© 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. 40419
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     consegu
    -0.31
     cubes
    -0.28
     Gund
    -0.27
     cube
    -0.26
    å®ļæľŁ
    -0.26
    æ°ij
    -0.26
    å¾Ĺ罪
    -0.26
    客è¿IJ
    -0.25
     cub
    -0.25
    annon
    -0.25
    POSITIVE LOGITS
    plx
    0.33
    ç¬ŀ
    0.30
    (HTTP
    0.27
    æ°ĺ
    0.27
    :NS
    0.26
    (NS
    0.25
    tors
    0.25
     tả
    0.24
    ael
    0.24
    صÙĪÙħ
    0.24
    Activations Density 0.174%

    No Known Activations