© 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. 39938
    Prev
    Next
    INDEX
    Explanations

    Names and initials

    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
     Nun
    -0.29
    ÑĥÑĢ
    -0.27
    è§Ĩ
    -0.27
    /tags
    -0.26
    unan
    -0.26
    icer
    -0.26
    wart
    -0.26
    ä¼Ľ
    -0.25
     Burr
    -0.25
    uren
    -0.25
    POSITIVE LOGITS
     travel
    0.27
    clave
    0.25
    _soc
    0.24
    opensource
    0.24
    Travel
    0.24
    usercontent
    0.24
    soup
    0.23
    è¯Ħå®ļ
    0.23
    communications
    0.23
    bound
    0.23
    Activations Density 0.030%

    No Known Activations