© 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. 149964
    Prev
    Next
    INDEX
    Explanations

    Code snippets and forum discussions

    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
    aeda
    -0.29
    iore
    -0.29
    çĦ¶æĺ¯
    -0.28
    eller
    -0.26
     influence
    -0.24
    é¢Ĩ导
    -0.24
    Ster
    -0.23
    çŁ³
    -0.23
    core
    -0.23
     oczywiÅĽcie
    -0.23
    POSITIVE LOGITS
    åŀĵ
    0.28
    家ä½ı
    0.27
    æĭĻ
    0.25
    åĵī
    0.24
    ungal
    0.24
    !',
    0.24
    uplic
    0.24
    æĪij说
    0.24
    æĢ§å¼º
    0.24
    åįģä¸ĩ
    0.23
    Activations Density 0.134%

    No Known Activations