© 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. 14-TRANSCODER-HP
    7. 41333
    Prev
    Next
    INDEX
    Explanations

    ux

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÑģÑĤÑĢ
    -0.27
    ret
    -0.27
    stitute
    -0.27
     compos
    -0.26
    å¾Ī
    -0.24
    ipation
    -0.24
    Miss
    -0.24
    struments
    -0.24
    sez
    -0.24
    ä¼´
    -0.24
    POSITIVE LOGITS
    ker
    0.27
    oyer
    0.26
    KER
    0.26
    duino
    0.26
     arous
    0.25
    lide
    0.25
    -front
    0.25
     FRONT
    0.24
     Front
    0.24
    çģµæ´»
    0.24
    Activations Density 0.106%

    No Known Activations