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. 109810
    Prev
    Next
    INDEX
    Explanations

    Code and programming

    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
    resultado
    -0.08
    ثم
    -0.07
    佸
    -0.07
    矧
    -0.07
     intersects
    -0.07
    完整热
    -0.07
    突发事件
    -0.07
     Thomson
    -0.07
     fiyatları
    -0.07
    \Entity
    -0.06
    POSITIVE LOGITS
    bfd
    0.08
    限制
    0.07
    __.__
    0.07
    Pad
    0.07
    buff
    0.07
    小店
    0.06
    PACK
    0.06
    ﺿ
    0.06
     �
    0.06
    distance
    0.06
    Activations Density 0.873%

    No Known Activations