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. 29769
    Prev
    Next
    INDEX
    Explanations

    desirable outcome

    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
    WER
    -0.07
    zheimer
    -0.07
    告
    -0.07
     Fetch
    -0.07
    以至于
    -0.07
    occasion
    -0.06
    fter
    -0.06
     genu
    -0.06
     squeeze
    -0.06
     Conclusion
    -0.06
    POSITIVE LOGITS
    _measure
    0.07
     bonded
    0.07
    Domain
    0.07
    传导
    0.06
    �
    0.06
     loaf
    0.06
    En
    0.06
    良かった
    0.06
     Aud
    0.06
    好感
    0.06
    Activations Density 0.024%

    No Known Activations