© 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. 109005
    Prev
    Next
    INDEX
    Explanations

    code

    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
    æİĸ
    -0.30
    _superuser
    -0.28
     Wer
    -0.26
    )||
    -0.25
    .heroku
    -0.25
    .UTF
    -0.24
    __.__
    -0.24
    ||↵
    -0.24
     seedu
    -0.24
    езÑĥлÑĮÑĤ
    -0.23
    POSITIVE LOGITS
    виз
    0.31
    çħ§
    0.29
     meas
    0.28
     pages
    0.27
    贪婪
    0.26
    æĿľ
    0.25
    åľ¨çĶŁæ´»ä¸Ń
    0.25
    templ
    0.25
    åĩĨ
    0.24
     dimension
    0.24
    Activations Density 0.925%

    No Known Activations