© 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. 32-TRANSCODER-HP
    7. 44040
    Prev
    Next
    INDEX
    Explanations

    F

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     SIL
    -0.26
    icut
    -0.26
     ÑĢÑĥб
    -0.25
     duk
    -0.25
     quali
    -0.23
    .rabbit
    -0.23
    SU
    -0.23
    å®ıè§Ĥ
    -0.23
    SSERT
    -0.23
    å¹ħ度
    -0.23
    POSITIVE LOGITS
    FA
    0.27
    ä¸ŃåĽ½äºº
    0.27
    è¿ĻæĿ¡
    0.25
    æĮ¯åħ´
    0.25
    uggestions
    0.25
    adin
    0.25
    çIJĨ论
    0.24
    ol
    0.24
    åī¯
    0.24
     Corn
    0.24
    Activations Density 0.000%

    No Known Activations