© 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. 52707
    Prev
    Next
    INDEX
    Explanations

    scientific and technical context

    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
    antas
    -0.28
    mere
    -0.26
    dff
    -0.26
    oka
    -0.26
    oir
    -0.26
    å¸ĸåŃIJ
    -0.25
    _ASSUME
    -0.24
    ,ID
    -0.24
    ç¾İçļĦ
    -0.24
    ardy
    -0.24
    POSITIVE LOGITS
     prevailing
    0.29
    èģĶéĢļ
    0.28
     prevalence
    0.28
     shifting
    0.27
     sustainability
    0.27
    缼è¡Į
    0.26
     hypers
    0.26
    atism
    0.26
     vic
    0.26
     intervention
    0.26
    Activations Density 0.034%

    No Known Activations