© 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. 44013
    Prev
    Next
    INDEX
    Explanations

    AX

    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
    åĿļæĮģ
    -0.57
    åłħæĮģ
    -0.46
     insist
    -0.42
    åĬªåĬĽ
    -0.39
    çļĦåĬªåĬĽ
    -0.38
     insisting
    -0.37
     insistence
    -0.37
     insists
    -0.36
    åĿļåĨ³
    -0.35
    è¦ģåĿļæĮģ
    -0.35
    POSITIVE LOGITS
    æĮģ
    0.40
     Ins
    0.38
     ins
    0.35
    Ins
    0.34
     held
    0.32
    pper
    0.31
    ç»Ŀç¼ĺ
    0.31
    .ins
    0.31
    åĴ¬
    0.31
    ins
    0.30
    Activations Density 0.001%

    No Known Activations