© 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. 11-RESID-POST-AA
    11. 92766
    Prev
    Next
    INDEX
    Explanations

    Math questions

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.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
    ;

↵
    -0.07
     לשמור
    -0.07
     coraz
    -0.07
     driven
    -0.06
     {?>↵
    -0.06
     required
    -0.06
     권
    -0.06
                                                    ↵
    -0.06
    Ẽ
    -0.06
    POSITIVE LOGITS
    异
    0.08
    psych
    0.07
    囫
    0.07
     InternalEnumerator
    0.07
     BAD
    0.07
     gradual
    0.07
    专业
    0.07
     Kul
    0.07
    无数
    0.07
     positively
    0.07
    Activations Density 0.003%

    No Known Activations