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. 56401
    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
     overrun
    -0.07
    就不能
    -0.07
    atsapp
    -0.07
    ToListAsync
    -0.07
    -w
    -0.07
    usk
    -0.07
    .timeScale
    -0.07
    他会
    -0.06
     nửa
    -0.06
    男朋友
    -0.06
    POSITIVE LOGITS
    Targets
    0.09
     records
    0.08
     trains
    0.07
     qued
    0.07
     dài
    0.07
    源于
    0.07
    (ball
    0.07
     trick
    0.07
     tutorials
    0.06
    Writer
    0.06
    Activations Density 0.017%

    No Known Activations