© 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. 52719
    Prev
    Next
    INDEX
    Explanations

    Animal behavior/medical contexts

    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
    feeds
    -0.28
    ies
    -0.28
     Nations
    -0.28
    ÑĮÑİ
    -0.27
     feeds
    -0.26
    NS
    -0.25
     Treaty
    -0.25
    elah
    -0.24
    iji
    -0.24
    tec
    -0.24
    POSITIVE LOGITS
    manual
    0.26
    è¿İ
    0.25
    rics
    0.25
    åĽ½éĻħæľºåľº
    0.24
     Kane
    0.24
     kep
    0.24
    rene
    0.23
    -guard
    0.23
    /activity
    0.23
    quot
    0.23
    Activations Density 0.014%

    No Known Activations