© 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. 98932
    Prev
    Next
    INDEX
    Explanations

    Publication

    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
    andel
    -0.28
    geh
    -0.27
    æĢ»
    -0.24
     ::=
    -0.24
    /loading
    -0.23
     mediated
    -0.23
    elige
    -0.23
    нÑıÑĤ
    -0.23
     enumerated
    -0.23
    âĶ
    -0.23
    POSITIVE LOGITS
    è¿ijæĹ¥
    0.31
     in
    0.31
    åľ¨ä»Ĭå¹´
    0.29
    æĹ¥åīį
    0.28
    arez
    0.28
     recently
    0.27
    èıĬ
    0.26
     Hispan
    0.25
     recent
    0.25
    åīįåĩłå¤©
    0.25
    Activations Density 0.019%

    No Known Activations