© 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. 52746
    Prev
    Next
    INDEX
    Explanations

    foreign language texts

    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
    ç¡Į
    -0.31
     tslint
    -0.30
     Assass
    -0.28
    Alchemy
    -0.27
    _fit
    -0.26
    unner
    -0.26
    æµģåħ¥
    -0.26
    vi
    -0.26
    Fit
    -0.25
    ethyl
    -0.24
    POSITIVE LOGITS
     comp
    0.35
    angep
    0.30
    ivist
    0.30
    _resolver
    0.28
     ser
    0.28
    apes
    0.28
    adel
    0.27
     ver
    0.27
     comps
    0.27
     acc
    0.27
    Activations Density 0.077%

    No Known Activations