© 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. 130940
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    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
    abcdefghijkl
    -0.28
     Mild
    -0.28
    olith
    -0.26
    ä¸į管æĺ¯
    -0.26
    oken
    -0.25
    аÑĤоÑĢ
    -0.25
    ocos
    -0.24
    oped
    -0.24
    umbles
    -0.24
    rong
    -0.24
    POSITIVE LOGITS
     +:+
    0.27
     programming
    0.26
    quake
    0.26
    çĻ¾åĪĨä¹ĭ
    0.25
     yourselves
    0.25
    亲è¿ij
    0.25
     im
    0.25
     recursion
    0.25
    æĸ¹ä¾¿
    0.25
     uns
    0.25
    Activations Density 26.578%

    No Known Activations