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. 15-RESID-POST-AA
    6. 45545
    Prev
    Next
    INDEX
    Explanations

    _now

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    승
    -0.07
    urface
    -0.07
    徜
    -0.07
     Dodge
    -0.07
    -flag
    -0.07
    _TASK
    -0.06
    byte
    -0.06
     выпуск
    -0.06
     STAR
    -0.06
     dart
    -0.06
    POSITIVE LOGITS
     objections
    0.07
     ffmpeg
    0.07
     *↵↵↵
    0.06
     должен
    0.06
    iguiente
    0.06
    _invalid
    0.06
    当之无愧
    0.06
    iaz
    0.06
    Ο
    0.06
    illegal
    0.06
    Activations Density 0.000%

    No Known Activations