© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 25949
    Prev
    Next
    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash

    This neuron activates on interrogative content—questions or question phrases (WH-words and sentences asking "what/why/how/are...").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _peer
    -0.07
    	pos
    -0.07
     Singles
    -0.07
    pdata
    -0.06
     spoiled
    -0.06
     lav
    -0.06
    gio
    -0.06
    祕
    -0.06
    /sweetalert
    -0.06
    🍠
    -0.06
    POSITIVE LOGITS
    ynamodb
    0.07
    ENCHMARK
    0.07
    Concat
    0.07
    细细
    0.07
    azure
    0.07
    Quite
    0.07
    iron
    0.07
    merge
    0.07
     Updated
    0.07
    technical
    0.07
    Activations Density 0.104%

    No Known Activations