© 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. 23-RESID-POST-AA
    11. 504
    Prev
    Next
    INDEX
    Explanations

    software dependency injection

    np_max-act-logits · gemini-2.0-flash
    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
     상
    -0.07
    suspend
    -0.07
     נ
    -0.07
    unic
    -0.07
     עשוי
    -0.06
    .uc
    -0.06
    تأ
    -0.06
     getConfig
    -0.06
    สาม
    -0.06
    销
    -0.06
    POSITIVE LOGITS
     minced
    0.07
     Chore
    0.07
    مشاريع
    0.07
    .hh
    0.07
    唐宇
    0.07
    的步伐
    0.06
    👉
    0.06
     inspiration
    0.06
    恒大
    0.06
    هد
    0.06
    Activations Density 0.011%

    No Known Activations