© 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. 64105
    Prev
    Next
    INDEX
    Explanations

    code/computing

    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
     fol
    -0.27
     gerne
    -0.27
     Fol
    -0.26
    _PULL
    -0.26
    ughter
    -0.25
    fol
    -0.24
     rap
    -0.24
    ÑĢад
    -0.24
     leven
    -0.24
     afl
    -0.23
    POSITIVE LOGITS
    éģĵçIJĨ
    0.27
    ijke
    0.27
    ansion
    0.27
    ackBar
    0.26
    nge
    0.26
    ä¸Ģåı¥è¯Ŀ
    0.26
    jas
    0.25
    _conf
    0.25
    é¦ĸ
    0.25
    羣çIJĨ
    0.25
    Activations Density 20.828%

    No Known Activations