© 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. 140864
    Prev
    Next
    INDEX
    Explanations

    Numbers and rankings

    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
    umat
    -0.35
    eli
    -0.28
    vere
    -0.27
    _priv
    -0.26
    át
    -0.26
    ãĥĹãĥ©ãĤ¤
    -0.26
    æį¶
    -0.25
    zo
    -0.25
    为ä¹ĭ
    -0.25
     Wig
    -0.24
    POSITIVE LOGITS
     either
    0.50
    either
    0.45
    Either
    0.43
     Either
    0.38
    è¦ģä¹Ī
    0.37
     both
    0.37
     zarówno
    0.36
     både
    0.35
     EITHER
    0.34
    æĹ¢æĺ¯
    0.34
    Activations Density 37.180%

    No Known Activations