© 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. 97320
    Prev
    Next
    INDEX
    Explanations

    PDF

    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
    Not in Any Lists

    No Comments

    Negative Logits
    erde
    -0.27
    ered
    -0.26
    tsy
    -0.26
    etu
    -0.25
    =back
    -0.24
    ured
    -0.24
    iedo
    -0.23
    驾é©Ń
    -0.23
     kc
    -0.23
    çªĺ
    -0.23
    POSITIVE LOGITS
    Sil
    0.28
    æľĢåŁºæľ¬
    0.25
    agraph
    0.25
    æµĻ
    0.25
    åij¨åĪĬ
    0.24
     softened
    0.23
    {|
    0.23
    åħ¬ç½ijå®īå¤ĩ
    0.23
    Formats
    0.23
    centre
    0.22
    Activations Density 0.028%

    No Known Activations