© 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. 9-TRANSCODER-HP
    7. 29929
    Prev
    Next
    INDEX
    Explanations

    disposal of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olor
    -0.26
    交
    -0.25
    æľº
    -0.25
     Credits
    -0.24
     particip
    -0.24
    æľīä¿¡å¿ĥ
    -0.24
     Prop
    -0.24
    peq
    -0.24
     Pret
    -0.23
    æī¿
    -0.23
    POSITIVE LOGITS
    ddl
    0.33
    åįļ客
    0.25
    uez
    0.25
    isi
    0.25
    åħ¬ä¼Ĺåı·
    0.25
     Bannon
    0.24
     Shea
    0.24
    ÑģлÑĥж
    0.23
    olla
    0.23
    aternity
    0.23
    Activations Density 0.811%

    No Known Activations