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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 96636
    Prev
    Next
    INDEX
    Explanations

    people, roles, and titles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    宣åijĬ
    -0.29
    (CONFIG
    -0.29
    udas
    -0.27
    çŀ©
    -0.26
    çĻ½éĽª
    -0.25
    untime
    -0.25
    éĺ³åı°
    -0.24
    åĽ½éĻħåIJĪä½ľ
    -0.24
    ä¿Ŀè¯ģ
    -0.24
    fld
    -0.24
    POSITIVE LOGITS
     recently
    0.30
    æľĢè¿ij
    0.24
     Bi
    0.24
    edit
    0.24
    oop
    0.24
     most
    0.24
    agus
    0.24
    æİ¥æīĭ
    0.23
    илÑĮ
    0.23
    CLU
    0.23
    Activations Density 0.102%

    No Known Activations