© 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. 52706
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
    åįģäºĶ
    -0.30
    icut
    -0.29
    åįģä¸ĥ
    -0.27
    äºĮåįģ
    -0.27
     infl
    -0.27
    åįģä¸ĥæĿ¡
    -0.26
    arı
    -0.26
    icularly
    -0.24
     seven
    -0.24
    aw
    -0.24
    POSITIVE LOGITS
    3
    0.36
    haul
    0.29
     Electrical
    0.28
    uld
    0.27
    4
    0.27
    6
    0.26
    enville
    0.25
    å¢Ł
    0.25
    aviours
    0.25
    UA
    0.25
    Activations Density 0.023%

    No Known Activations