© 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. 24-TRANSCODER-HP
    7. 150365
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĽ´æĺ¯
    -0.28
    tors
    -0.28
    æĮģä»ĵ
    -0.27
     Twe
    -0.26
    ilon
    -0.25
     Handy
    -0.24
    积æŀģåıĤä¸İ
    -0.23
    undy
    -0.23
     QtWidgets
    -0.23
    å½ĵä¹ĭ
    -0.23
    POSITIVE LOGITS
    omba
    0.28
    .bmp
    0.28
     Romanian
    0.26
    滩
    0.25
     repaired
    0.24
    eria
    0.24
    Vi
    0.24
    æĥ³åĪ°äºĨ
    0.24
    /Area
    0.24
     roasted
    0.23
    Activations Density 1.126%

    No Known Activations