© 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. 33-TRANSCODER-HP
    7. 53390
    Prev
    Next
    INDEX
    Explanations

    Punctuation and special characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    essen
    -0.26
    æıIJéĹ®
    -0.26
    els
    -0.26
    ä¸ŃåIJ«æľī
    -0.24
     nắm
    -0.24
    éĥ½ä¸įæĺ¯
    -0.23
    æĬ¢æĬĵ
    -0.23
    pton
    -0.23
    åħ³å¿ĥ
    -0.23
     má»Ŀi
    -0.23
    POSITIVE LOGITS
     »,
    0.34
    @",
    0.34
    ",
    0.34
    ',//
    0.34
    ï¼ģ",
    0.33
    ãĢĭï¼Į
    0.33
    “,
    0.32
    ”ï¼Į
    0.32
     */,
    0.31
    %ï¼Į
    0.31
    Activations Density 0.248%

    No Known Activations