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. 23-RESID-POST-AA
    6. 130841
    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    �
    -0.07
    วรรณ
    -0.07
    귿
    -0.07
     Easter
    -0.07
     Dialog
    -0.06
     narz
    -0.06
     pieniąd
    -0.06
    .mc
    -0.06
     trách
    -0.06
    𫓯
    -0.06
    POSITIVE LOGITS
     Confederate
    0.07
    委副书记
    0.07
    ‑
    0.06
    なかなか
    0.06
     gonna
    0.06
    ꀰ
    0.06
    群里
    0.06
    _green
    0.06
    _CENTER
    0.06
    _destroy
    0.06
    Activations Density 0.026%

    No Known Activations