© 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. 35-TRANSCODER-HP
    7. 38972
    Prev
    Next
    INDEX
    Explanations

    Apache Software Foundation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fuse
    -0.29
     fuse
    -0.28
    级以ä¸Ĭ
    -0.27
    èµĺ
    -0.25
    imum
    -0.25
    çĮ¥
    -0.24
    igm
    -0.24
     dame
    -0.24
    éĵĨ
    -0.24
     migr
    -0.24
    POSITIVE LOGITS
    ola
    0.50
    olla
    0.46
    ols
    0.46
    olas
    0.46
    olan
    0.45
    on
    0.43
    ollar
    0.42
    .ol
    0.40
    OLA
    0.40
    ol
    0.39
    Activations Density 0.024%

    No Known Activations