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. 131048
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    <main
    -0.08
    ManagedObject
    -0.07
    ält
    -0.07
    .mob
    -0.07
     счет
    -0.07
     Board
    -0.07
    _MONTH
    -0.07
     выбира
    -0.07
    cope
    -0.07
     exposing
    -0.07
    POSITIVE LOGITS
    */↵↵
    0.07
    Broadcast
    0.07
    .`,↵
    0.07
    说着
    0.07
    铿
    0.07
    ROPERTY
    0.07
    数千
    0.06
    +z
    0.06
    泃
    0.06
    (tokens
    0.06
    Activations Density 0.012%

    No Known Activations