© 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. 111334
    Prev
    Next
    INDEX
    Explanations

    surrounded

    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
     anguish
    -0.08
    转型
    -0.08
    支线
    -0.07
    还是比较
    -0.07
     khá
    -0.07
    asin
    -0.07
    实训
    -0.07
     ●
    -0.07
    辽宁
    -0.07
    ):(
    -0.06
    POSITIVE LOGITS
     forced
    0.07
    𫵷
    0.07
     ];↵↵
    0.07
    Mouse
    0.06
     judge
    0.06
     מצד
    0.06
     pipe
    0.06
    Roboto
    0.06
    DESC
    0.06
     recib
    0.06
    Activations Density 0.021%

    No Known Activations