© 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. 20-TRANSCODER-HP
    7. 130125
    Prev
    Next
    INDEX
    Explanations

    omer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tracked
    -0.29
    ĵį
    -0.28
     refin
    -0.27
    æĬĬèĩªå·±
    -0.26
     Zh
    -0.26
     THR
    -0.25
    hk
    -0.24
    HONE
    -0.24
     captured
    -0.24
    ickets
    -0.24
    POSITIVE LOGITS
    æĹ¥æĬ¥è®°èĢħ
    0.26
    -esteem
    0.25
    .Tx
    0.24
    prowad
    0.23
    irling
    0.23
    @c
    0.23
    -themed
    0.23
    covery
    0.23
    *y
    0.23
    proposal
    0.23
    Activations Density 13.717%

    No Known Activations