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. 72462
    Prev
    Next
    INDEX
    Explanations

    faith and healing stories

    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
     (;;
    -0.07
    شؤ
    -0.07
     Annex
    -0.06
    /vnd
    -0.06
    icopt
    -0.06
    Facebook
    -0.06
     StringTokenizer
    -0.06
     anarchists
    -0.06
    .UltraWin
    -0.06
    ‰
    -0.06
    POSITIVE LOGITS
    ↵    ↵    ↵
    0.08
    亲身
    0.07
     prescribing
    0.07
    ()],↵
    0.07
    픠
    0.07
     PGA
    0.07
     **
    0.07
    てくる
    0.07
    )(
    0.07
     Thanksgiving
    0.07
    Activations Density 0.003%

    No Known Activations