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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 75440
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    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
    경제
    -0.07
    	op
    -0.07
     또한
    -0.07
    られる
    -0.07
    'email
    -0.07
     richtig
    -0.07
     PEM
    -0.06
     bruk
    -0.06
    _ok
    -0.06
    خدام
    -0.06
    POSITIVE LOGITS
    غض
    0.07
     עצ
    0.07
     PHI
    0.07
    جز
    0.06
    极力
    0.06
     послед
    0.06
    写作
    0.06
    Expose
    0.06
    꽐
    0.06
    エネル
    0.06
    Activations Density 0.320%

    No Known Activations