Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 31433
    Prev
    Next
    INDEX
    Explanations

    re

    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
    赌博
    -0.07
    喇
    -0.07
     onc
    -0.07
    ゼ
    -0.07
     nguyện
    -0.07
    置业
    -0.07
    经济发展
    -0.07
     serene
    -0.07
    能源
    -0.07
    gens
    -0.06
    POSITIVE LOGITS
    ичество
    0.08
    >{@
    0.07
    껌
    0.07
    مور
    0.06
     COLUMN
    0.06
    被困
    0.06
    ISCO
    0.06
    月以来
    0.06
     tir
    0.06
     자기
    0.06
    Activations Density 0.002%

    No Known Activations