© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 5722
    Prev
    Next
    INDEX
    Explanations

    computer/app related

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     השי
    -0.07
    ;;↵↵
    -0.06
     зависим
    -0.06
    萸
    -0.06
    อำนวยความ
    -0.06
    娃
    -0.06
    שווי
    -0.06
     attends
    -0.06
    apping
    -0.06
    鼯
    -0.06
    POSITIVE LOGITS
    ▍
    0.07
    Forbidden
    0.07
    修养
    0.07
    民航
    0.07
    _fault
    0.07
     fixing
    0.07
    手套
    0.07
    -first
    0.07
    _REFRESH
    0.07
    Trade
    0.07
    Activations Density 0.205%

    No Known Activations