© 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. 8025
    Prev
    Next
    INDEX
    Explanations

    Code-related?

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åĮı
    -0.26
    è¿Ļ对
    -0.26
    宿
    -0.26
    .Spring
    -0.25
    vat
    -0.25
    æ¸
    -0.24
    æ¯ĵ
    -0.24
    yy
    -0.24
    Ñıм
    -0.24
    .getLog
    -0.24
    POSITIVE LOGITS
    à¸Ĭะ
    0.28
    ymb
    0.28
    owering
    0.27
    èĥĮåĮħ
    0.26
    azine
    0.25
    _attempts
    0.25
     Lancaster
    0.25
    责任åĪ¶
    0.25
    unga
    0.25
    coe
    0.25
    Activations Density 0.004%

    No Known Activations