© 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. 52709
    Prev
    Next
    INDEX
    Explanations

    Code and math equations

    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
     Sour
    -0.26
     Neu
    -0.25
    éĻ¡
    -0.25
    çĩķ
    -0.25
    ç²¹
    -0.24
    jing
    -0.24
    opro
    -0.24
    arkin
    -0.23
     popping
    -0.23
     tabindex
    -0.23
    POSITIVE LOGITS
    áĥ¥
    0.28
    åı¯ä»¥è¯´
    0.28
    allax
    0.26
    æī©
    0.26
    obb
    0.25
    æµ·å¤ĸå¸Ĥåľº
    0.24
     zip
    0.24
    der
    0.24
    iges
    0.24
    ders
    0.24
    Activations Density 0.021%

    No Known Activations