© 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. 54720
    Prev
    Next
    INDEX
    Explanations

    portrait

    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
     ETA
    -0.26
     Translate
    -0.25
    bef
    -0.24
    å¤ĸåªĴ
    -0.24
     art
    -0.24
    浯
    -0.24
    西æĸ¹
    -0.24
    arts
    -0.24
    ç§ģ人
    -0.24
    ART
    -0.23
    POSITIVE LOGITS
    uple
    0.28
    é¡¿
    0.26
     nc
    0.26
    lyph
    0.26
    uous
    0.25
    Emer
    0.25
    ÑĢи
    0.25
    ific
    0.25
     tup
    0.24
     emerg
    0.24
    Activations Density 0.015%

    No Known Activations