© 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. 62565
    Prev
    Next
    INDEX
    Explanations

    comparative/escalating language

    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
    å°Ħæīĭ
    -0.30
     full
    -0.27
    [OF
    -0.25
    åħ¨æĹ¥
    -0.24
    lobs
    -0.24
    åĩĨ
    -0.24
    ç½ijæł¼
    -0.24
     probabilities
    -0.23
    å°Ħ
    -0.23
    mins
    -0.23
    POSITIVE LOGITS
    ä¸įèĥ½åĨį
    0.34
    ä¹ŁæĹłæ³ķ
    0.29
     Nope
    0.29
    æĹłæ³ķ
    0.29
    éĥ½ä¸įæķ¢
    0.28
     beyond
    0.28
     further
    0.28
    ä¸įåºĶ
    0.28
     cannot
    0.28
    éĥ½æĹłæ³ķ
    0.28
    Activations Density 44.213%

    No Known Activations