© 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. 27-TRANSCODER-HP
    7. 58628
    Prev
    Next
    INDEX
    Explanations

    non-English fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    .nan
    -0.26
    fixtures
    -0.26
    иÑģк
    -0.25
    天æ°Ķ
    -0.25
     dizzy
    -0.25
    è¿IJèIJ¥
    -0.24
    unfold
    -0.24
     virt
    -0.23
     unf
    -0.23
    å½ĵåľ°çļĦ
    -0.23
    POSITIVE LOGITS
    è¾±
    0.32
    chal
    0.31
    ationToken
    0.28
    å¢ŀé«ĺ
    0.27
    èĢ»
    0.27
    éĢĨè¡Į
    0.26
    alle
    0.26
    aurus
    0.26
    åĢĴ
    0.26
    串
    0.25
    Activations Density 0.117%

    No Known Activations