© 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. 95661
    Prev
    Next
    INDEX
    Explanations

    scanned documents and code

    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
    té
    -0.27
    tsy
    -0.27
     talks
    -0.25
    tal
    -0.25
     talking
    -0.25
    ä½Ī
    -0.25
    大家éĥ½åľ¨
    -0.25
     proceeding
    -0.24
     sidew
    -0.24
    廣
    -0.23
    POSITIVE LOGITS
    è¿ĩ
    0.31
    ả
    0.28
    æľŁ
    0.28
    umper
    0.27
    mutations
    0.26
    ordination
    0.25
    immune
    0.24
    immers
    0.24
    èį«
    0.24
    elt
    0.23
    Activations Density 0.002%

    No Known Activations