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. 57007
    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_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
    /A
    -0.06
     swe
    -0.06
    "A
    -0.06
    流
    -0.06
     dis
    -0.06
    .Material
    -0.06
     Won
    -0.06
    ohn
    -0.06
    plits
    -0.06
    onds
    -0.06
    POSITIVE LOGITS
     pronounce
    0.07
    录取
    0.07
     gases
    0.07
     enactment
    0.07
     każ
    0.07
    (".");↵
    0.07
    ////////////////////////////////////////////////////
    0.07
     interrog
    0.07
    (API
    0.06
    אפשר
    0.06
    Activations Density 0.007%

    No Known Activations