© 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. 22-TRANSCODER-HP
    7. 130963
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     ""
    -0.30
    ↵↵
    -0.28
    ↵
    -0.27
    /
    -0.27
    rase
    -0.27
    è¾ĥ
    -0.27
    ()
    -0.26
    è¾¹
    -0.25
    M
    -0.24
     []
    -0.24
    POSITIVE LOGITS
    **,
    0.47
    .*,
    0.42
     ...,
    0.42
    =?,
    0.41
    */,
    0.39
    ...,
    0.39
     &,
    0.39
    \",
    0.39
    ®,
    0.38
    ãĢij,
    0.37
    Activations Density 0.004%

    No Known Activations