© 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. 25-TRANSCODER-HP
    7. 108650
    Prev
    Next
    INDEX
    Explanations

    has

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    缮çļĦ
    -0.27
    å¥
    -0.25
    inc
    -0.25
    èĩ¾
    -0.25
    缮çļĦæĺ¯
    -0.24
    ú
    -0.24
    æĦıä¹īä¸ĬçļĦ
    -0.24
    å®ļéĩı
    -0.23
    çļĦ缮çļĦ
    -0.23
     Anthem
    -0.23
    POSITIVE LOGITS
    æľīä¸Ģ个
    0.28
    has
    0.27
    ä¸Ģç§į
    0.26
     ______
    0.26
     has
    0.25
    åĩłä¸ª
    0.25
    æĢ»åħ±
    0.25
    ä¸ĢæĹı
    0.25
    ä¸Ģåıªæīĭ
    0.25
     current
    0.24
    Activations Density 0.217%

    No Known Activations