© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 14710
    Prev
    Next
    INDEX
    Explanations

    omer

    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
    自信
    -0.08
    _IMPLEMENT
    -0.08
    霸道
    -0.07
    궂
    -0.07
    참
    -0.07
    贼
    -0.07
     Visit
    -0.07
     candid
    -0.07
    順
    -0.07
    留言
    -0.07
    POSITIVE LOGITS
    tein
    0.07
    𥕢
    0.06
     heter
    0.06
     Protein
    0.06
     Who
    0.06
    護
    0.06
     כמו
    0.06
    金银
    0.06
     exploited
    0.06
     dressing
    0.06
    Activations Density 0.011%

    No Known Activations