© 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. 33-TRANSCODER-HP
    7. 54831
    Prev
    Next
    INDEX
    Explanations

    foreign names or words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ibase
    -0.33
    åĽŀåIJĪ
    -0.31
    icontrol
    -0.27
     forge
    -0.27
    ursors
    -0.27
    upd
    -0.26
    odyn
    -0.26
    ÙĪرد
    -0.25
    _clr
    -0.25
    æĶĺ
    -0.25
    POSITIVE LOGITS
    quo
    0.28
    eld
    0.28
    èī¯
    0.27
    SL
    0.27
    å¼ķ
    0.27
    yo
    0.25
    KO
    0.25
    rok
    0.25
    FS
    0.25
    sek
    0.25
    Activations Density 0.005%

    No Known Activations