© 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. 107624
    Prev
    Next
    INDEX
    Explanations

    Geographical descriptions

    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
    anity
    -0.30
    é½IJ
    -0.26
    ç«
    -0.26
    liers
    -0.25
    讫
    -0.24
    é½Ĭ
    -0.24
     Floyd
    -0.24
    LError
    -0.24
    .getAs
    -0.23
    åĽ½åĬ¡
    -0.23
    POSITIVE LOGITS
     searchable
    0.25
    -Isl
    0.25
     çocuk
    0.25
     shine
    0.24
    CN
    0.24
    æĽĻåħī
    0.24
    myp
    0.23
     shines
    0.23
    CHE
    0.23
    .Classes
    0.23
    Activations Density 10.022%

    No Known Activations