© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 43
    Prev
    Next
    INDEX
    Explanations

    fictional stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oui
    -0.29
    é¢Ħç®Ĺ
    -0.27
    grow
    -0.27
    ä¼ļä¸Ĭ
    -0.26
    loor
    -0.25
    æĪIJéķ¿
    -0.24
    éĶ¤
    -0.24
    ä¾Ŀæ³ķ
    -0.23
     ÑĢожд
    -0.23
    èı
    -0.23
    POSITIVE LOGITS
    fac
    0.24
    utas
    0.24
    <cv
    0.24
    ãĤĭãģĵãģ¨ãģĮãģ§ãģįãģ¾ãģĻ
    0.24
     ung
    0.23
    faction
    0.23
    ÅĤatw
    0.23
     Dame
    0.23
    缮ãģ®
    0.23
    ackson
    0.23
    Activations Density 0.004%

    No Known Activations