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. 71941
    Prev
    Next
    INDEX
    Explanations

    suppressing/restricting

    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
     shaders
    -0.08
     giờ
    -0.08
    挛
    -0.07
     tôi
    -0.07
    鲀
    -0.07
     chocolate
    -0.07
     intelligent
    -0.07
    zs
    -0.07
    回家
    -0.07
    _IOC
    -0.07
    POSITIVE LOGITS
    已于
    0.07
     Faul
    0.07
    .prompt
    0.07
     Pussy
    0.07
    先锋
    0.07
    CAST
    0.07
    Restart
    0.07
    主导
    0.07
    ]*(
    0.06
    /n
    0.06
    Activations Density 0.002%

    No Known Activations