© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 109313
    Prev
    Next
    INDEX
    Explanations

    pitch

    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
    Negative Logits
     eher
    -0.27
     Mark
    -0.25
    cond
    -0.24
    ivre
    -0.24
    ../../../
    -0.24
    nger
    -0.24
    ymous
    -0.24
    ycz
    -0.24
    o
    -0.23
    uth
    -0.23
    POSITIVE LOGITS
    (es
    0.33
    APPLE
    0.26
    åijĺ
    0.26
    èĩ£
    0.25
     amb
    0.25
    -offs
    0.24
    !--
    0.24
    ç§ijåѦ
    0.24
    -au
    0.23
     inert
    0.22
    Activations Density 0.266%

    No Known Activations