© 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. 107292
    Prev
    Next
    INDEX
    Explanations

    road names

    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
    cba
    -0.28
    --[
    -0.26
     PMID
    -0.25
    bish
    -0.25
     Feinstein
    -0.25
    UBLE
    -0.25
    "--
    -0.25
    åºĶä»ĺ
    -0.24
     Statistics
    -0.24
     tijd
    -0.24
    POSITIVE LOGITS
    ç²¾
    0.29
    VRT
    0.28
    æĦ¿
    0.27
    arts
    0.25
    ýt
    0.25
    ictionary
    0.25
    æĪIJ年人
    0.25
    isObject
    0.25
     Buck
    0.24
    çłĢ
    0.23
    Activations Density 0.952%

    No Known Activations