© 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. 25-TRANSCODER-HP
    7. 106989
    Prev
    Next
    INDEX
    Explanations

    code/technical documentation snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æĢ»ä¼ļ
    -0.27
    éĤ®
    -0.27
     éc
    -0.26
    alnum
    -0.26
    åľ¨è¿ĩ渡
    -0.26
    ãģĬãĤĬ
    -0.26
    åģļ大åģļ强
    -0.26
    éĴ®
    -0.25
     overl
    -0.24
    past
    -0.24
    POSITIVE LOGITS
     HEADER
    0.26
    Shoot
    0.26
     pers
    0.26
    ply
    0.25
    åħļ
    0.25
    æ¯Ķçī¹
    0.25
    лев
    0.24
    è¿ŀ
    0.23
    inity
    0.23
    -cloud
    0.23
    Activations Density 0.120%

    No Known Activations