© 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. 107394
    Prev
    Next
    INDEX
    Explanations

    News excerpts

    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
    æĺ¯æĢİä¹Ī
    -0.27
     bootloader
    -0.27
    ryn
    -0.26
    merc
    -0.25
    indr
    -0.25
    æĺ¯å¦Ĥä½ķ
    -0.25
    èĥ½å¤Łåľ¨
    -0.25
    iler
    -0.24
    .appspot
    -0.24
    etal
    -0.24
    POSITIVE LOGITS
    toa
    0.27
     win
    0.26
    举äºļ
    0.26
    HEAD
    0.25
    è°
    0.25
    ÑĩеÑĤ
    0.25
    NAL
    0.24
    uster
    0.24
     servant
    0.24
    ç¥ī
    0.24
    Activations Density 1.018%

    No Known Activations