© 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. 52501
    Prev
    Next
    INDEX
    Explanations

    lymph

    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
     Oro
    -0.31
    èĤĺ
    -0.29
     subs
    -0.29
    orsi
    -0.27
    pill
    -0.26
     Straight
    -0.26
     Laure
    -0.26
     tá»ķ
    -0.25
    è¡¥
    -0.25
     Lake
    -0.25
    POSITIVE LOGITS
    éĨ®
    0.30
    оÑĩек
    0.29
    okin
    0.28
    ä¸Ģåı£æ°Ķ
    0.27
    oodle
    0.27
    itin
    0.26
    ëĵľë¦¬
    0.26
    axy
    0.26
    oder
    0.26
    ANEL
    0.26
    Activations Density 0.005%

    No Known Activations