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. 2298
    Prev
    Next
    INDEX
    Explanations

    structures

    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
     USER
    -0.07
    Ệ
    -0.07
    睾
    -0.07
     Enter
    -0.06
    geme
    -0.06
     кли
    -0.06
     doe
    -0.06
    双眼
    -0.06
     wk
    -0.06
    	before
    -0.06
    POSITIVE LOGITS
    Requirements
    0.07
     İslam
    0.07
     declined
    0.06
     الحديد
    0.06
     Har
    0.06
     removeFromSuperview
    0.06
     ска
    0.06
    ⵟ
    0.06
    olynomial
    0.06
    哱
    0.06
    Activations Density 0.007%

    No Known Activations