© 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. 130811
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ourd
    -0.29
    å¯Ħ
    -0.28
    explo
    -0.27
    ose
    -0.27
     enjoy
    -0.26
     moderne
    -0.26
    ĻĤ
    -0.25
    åŃ£åIJİ
    -0.24
    ifest
    -0.24
     enjoys
    -0.24
    POSITIVE LOGITS
     withheld
    0.30
     prefect
    0.28
    è´£ç¼ĸ
    0.27
    ìĹŃ
    0.27
    éĴ¤
    0.26
     inspected
    0.25
     unins
    0.25
     Omn
    0.25
    管å±Ģ
    0.25
     пÑĢоизведен
    0.25
    Activations Density 4.307%

    No Known Activations

    This feature has no known activations.