© 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. 142576
    Prev
    Next
    INDEX
    Explanations

    Technical and academic content

    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
    Negative Logits
    åħ¶å®ĥ
    -0.39
     other
    -0.38
    åħ¶ä»ĸ人
    -0.38
    åħ¶ä»ĸ
    -0.37
    others
    -0.37
    (other
    -0.35
    other
    -0.35
     others
    -0.35
    Other
    -0.34
    Others
    -0.34
    POSITIVE LOGITS
    éľīç´ł
    0.27
     Under
    0.26
    imson
    0.26
    edition
    0.26
    verity
    0.25
    ä»ĸåľ¨
    0.25
    æ¡ģ
    0.25
     Detail
    0.25
    redict
    0.24
    errat
    0.24
    Activations Density 64.687%

    No Known Activations