© 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. 23-TRANSCODER-HP
    7. 23739
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èµ·èįī
    -0.32
    ared
    -0.26
    æĹ¶å¸¸
    -0.25
    æĪĹ
    -0.25
    hem
    -0.25
    åħ¬æĬ¥
    -0.25
    inx
    -0.25
    á»ĩt
    -0.24
    explode
    -0.24
    æŶéļĶ
    -0.24
    POSITIVE LOGITS
    	catch
    0.25
    owie
    0.25
    æĺ¯æľĢ好çļĦ
    0.24
    æīĵè´¥
    0.24
    eg
    0.24
    à¸ģà¸Ķ
    0.23
    (ctrl
    0.23
    wald
    0.23
    avl
    0.23
     pretending
    0.23
    Activations Density 0.018%

    No Known Activations

    This feature has no known activations.