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. 88507
    Prev
    Next
    INDEX
    Explanations

    mixing and stirring

    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
    _correct
    -0.08
    hosts
    -0.08
    道教
    -0.07
    或許
    -0.07
    巡视
    -0.07
     الكوي
    -0.07
    プリン
    -0.07
    готов
    -0.07
         
    -0.07
    评估
    -0.07
    POSITIVE LOGITS
     בלי
    0.08
    🎼
    0.08
     VLC
    0.07
    _PWM
    0.07
    خدام
    0.07
    äche
    0.07
    ℧
    0.07
     needle
    0.07
    茛
    0.07
     HAND
    0.07
    Activations Density 0.021%

    No Known Activations