© 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. 85445
    Prev
    Next
    INDEX
    Explanations

    Yes

    np_max-act · gemini-2.0-flash

    starts of assistant responses and sentence or list openers (initial leading tokens at the beginning of a turn or item).

    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
     ${(
    -0.07
    riding
    -0.07
    .Container
    -0.06
    썰
    -0.06
    𝑁
    -0.06
    𝑇
    -0.06
     volleyball
    -0.06
     зарегист
    -0.06
    Following
    -0.06
    ⏬
    -0.06
    POSITIVE LOGITS
     hopes
    0.07
    /Graphics
    0.07
     callBack
    0.07
    -actions
    0.07
    wait
    0.07
    .unique
    0.07
     FStar
    0.06
    RESOURCE
    0.06
    much
    0.06
    十二五
    0.06
    Activations Density 0.097%

    No Known Activations