© 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. 23-TRANSCODER-HP
    7. 24936
    Prev
    Next
    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ern
    -0.28
     quant
    -0.24
     week
    -0.24
     “âĢ¦
    -0.24
    /fa
    -0.24
    anko
    -0.23
    åĽłä¸ºä»ĸ们
    -0.23
    æĿĸ
    -0.23
    /ay
    -0.23
    æĬĹçĻĮ
    -0.23
    POSITIVE LOGITS
    ross
    0.25
    is
    0.25
    ç°ĩ
    0.24
     MUT
    0.24
    fore
    0.24
    ãĥĤ
    0.24
    Mut
    0.24
     Aws
    0.24
    bm
    0.23
    è¿IJä½ľ
    0.23
    Activations Density 0.030%

    No Known Activations