© 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. 27-TRANSCODER-HP
    7. 9797
    Prev
    Next
    INDEX
    Explanations

    say "Sch" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    crit
    -0.28
    /cc
    -0.27
     Persons
    -0.25
    /Table
    -0.25
    metrical
    -0.24
    Directory
    -0.24
    ableObject
    -0.24
    persons
    -0.24
    preci
    -0.24
    -figure
    -0.24
    POSITIVE LOGITS
    alis
    0.25
    alo
    0.25
    (([
    0.25
    anko
    0.25
     vac
    0.25
    PAIR
    0.24
    EMPTY
    0.24
    æľīä¸Ģ天
    0.24
     Vac
    0.24
    空
    0.24
    Activations Density 0.810%

    No Known Activations