© 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. 108159
    Prev
    Next
    INDEX
    Explanations

    Code/technical documentation

    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
    uries
    -0.29
    ","\
    -0.29
    idan
    -0.27
    ä¿Ŀå®Ī
    -0.26
    asel
    -0.26
    é£İæļ´
    -0.25
    FLT
    -0.24
    ",{
    -0.24
    HELL
    -0.24
    沫
    -0.24
    POSITIVE LOGITS
    icot
    0.29
    åĪ¶æľį
    0.25
    ç»ĻåŃ©åŃIJ
    0.25
    ç»Ļå®Ŀå®Ŀ
    0.25
    otomy
    0.25
     ngoÃłi
    0.24
    uta
    0.24
     solved
    0.24
    J
    0.23
    æĢ»çļĦæĿ¥è¯´
    0.23
    Activations Density 0.126%

    No Known Activations