© 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. 42234
    Prev
    Next
    INDEX
    Explanations

    question marks

    np_max-act · gemini-2.0-flash

    interview-style questions and Q&A dialogue cues, especially interrogative lines and Q:/A: turns.

    oai_token-act-pair · gpt-5Triggered 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
    もなく
    -0.07
    同時に
    -0.07
     appeared
    -0.07
     Overflow
    -0.07
     Moran
    -0.06
    由于
    -0.06
    齇
    -0.06
     guesses
    -0.06
    _big
    -0.06
    打响
    -0.06
    POSITIVE LOGITS
    (|
    0.07
     install
    0.07
    wrap
    0.06
    /page
    0.06
     nghìn
    0.06
     sodium
    0.06
    让你
    0.06
     pf
    0.06
    _tiles
    0.06
     Blade
    0.06
    Activations Density 0.119%

    No Known Activations