© 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. 20-TRANSCODER-HP
    7. 142435
    Prev
    Next
    INDEX
    Explanations

    Choices, needs, or desires

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anel
    -0.28
    ä»İä¸Ń
    -0.27
    nect
    -0.27
    ä¸İæѤ
    -0.27
    åĴ«
    -0.27
    æľīéĻIJ
    -0.26
    ä¸ĭåįĬ
    -0.25
    èĥĮåIJİ
    -0.24
     uda
    -0.24
    .private
    -0.24
    POSITIVE LOGITS
     Walter
    0.25
    éĢ¼
    0.24
    (and
    0.24
    å¹´ä¹ĭä¹ħ
    0.24
     spread
    0.24
    خاÙħ
    0.24
    spread
    0.23
    yw
    0.23
    aku
    0.23
     anyway
    0.23
    Activations Density 15.517%

    No Known Activations