© 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. 41075
    Prev
    Next
    INDEX
    Explanations

    medical research

    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
    yscale
    -0.28
    iest
    -0.28
    _filters
    -0.26
    .Panel
    -0.26
    å¿ĥ头
    -0.26
    èĤ¼
    -0.25
    å¿ĥä¸ŃçļĦ
    -0.25
    .DEFINE
    -0.25
     Dw
    -0.24
    éļIJèĹı
    -0.24
    POSITIVE LOGITS
     Hockey
    0.28
     Hv
    0.26
    HI
    0.25
     Hanson
    0.25
    æĥ°
    0.25
     ÐŁÐµÑĤÑĢ
    0.25
    ä¹Łå¥½
    0.24
     mk
    0.24
    mk
    0.24
     Protestant
    0.24
    Activations Density 1.079%

    No Known Activations