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

    Neuronpedia

    APICircuit 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. 31275
    Prev
    Next
    INDEX
    Explanations

    patents and inventions

    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
    解放思想
    -0.08
    sher
    -0.07
    ꈍ
    -0.06
    .article
    -0.06
    pyx
    -0.06
    .POS
    -0.06
    .contents
    -0.06
    сложн
    -0.06
     getRandom
    -0.06
    森林公园
    -0.06
    POSITIVE LOGITS
    记录
    0.08
    实施
    0.07
     vern
    0.07
    ////↵
    0.07
     '}';↵
    0.07
     activating
    0.07
     확인
    0.07
    α
    0.07
    _record
    0.07
     "-"
    0.06
    Activations Density 0.049%

    No Known Activations