© 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. 9530
    Prev
    Next
    INDEX
    Explanations

    the

    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
    ä¸Ģç»ı
    -0.34
     weekdays
    -0.29
     fibre
    -0.29
    ãģ®ä¸Ģ
    -0.27
    åĩłå¹´åīį
    -0.26
    æĹ©ä¸Ĭ
    -0.26
    strand
    -0.25
     hå
    -0.25
     mould
    -0.25
    iday
    -0.24
    POSITIVE LOGITS
    uffer
    0.26
    _TM
    0.26
    ulkan
    0.26
     combined
    0.25
    extr
    0.25
     WHATSOEVER
    0.24
    æĪijè¦ģ
    0.24
    æŀª
    0.24
    ;break
    0.24
    è¶Ĭ
    0.23
    Activations Density 0.005%

    No Known Activations