Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 87789
    Prev
    Next
    INDEX
    Explanations

    by

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تناول
    -0.08
    尤为
    -0.07
    .middle
    -0.07
    涕
    -0.07
     Casinos
    -0.07
    -I
    -0.07
     Affiliate
    -0.06
     Polish
    -0.06
    脑
    -0.06
    치료
    -0.06
    POSITIVE LOGITS
    facet
    0.07
     stagnant
    0.07
    ']?>"
    0.07
    )...
    0.07
     suppressing
    0.07
    %%*/
    0.06
    arning
    0.06
    实行
    0.06
    -addon
    0.06
    toFloat
    0.06
    Activations Density 0.001%

    No Known Activations