© 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. 54581
    Prev
    Next
    INDEX
    Explanations

    partial passages

    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
    -ton
    -0.33
    Po
    -0.26
    umper
    -0.26
    assing
    -0.26
     po
    -0.26
     ton
    -0.25
    ARAM
    -0.25
    oce
    -0.24
    Ju
    -0.24
     Odin
    -0.24
    POSITIVE LOGITS
    iv
    0.26
    ов
    0.26
     capÃŃtulo
    0.26
     Partial
    0.25
    ixin
    0.25
     v
    0.25
    ä¹į
    0.25
    irus
    0.24
    第ä¸Ģ
    0.24
    çºł
    0.23
    Activations Density 0.012%

    No Known Activations