© 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. 108298
    Prev
    Next
    INDEX
    Explanations

    special symbols

    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
    认
    -0.28
    tractive
    -0.27
    iked
    -0.27
    çĨı
    -0.26
     Tod
    -0.26
    exclusive
    -0.25
    åĿIJ
    -0.25
    .Done
    -0.24
     ked
    -0.24
    æı
    -0.24
    POSITIVE LOGITS
    éĵī
    0.29
    [count
    0.27
     tán
    0.27
    åĪĨæķ£
    0.27
    [#
    0.25
    åıį转
    0.25
    è¿IJ转
    0.25
     something
    0.24
    çļĵ
    0.24
    å¹ķ
    0.24
    Activations Density 0.013%

    No Known Activations