© 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. 56699
    Prev
    Next
    INDEX
    Explanations

    of

    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
    æĻĤéĸĵ
    -0.26
    canf
    -0.26
     æŶéĹ´
    -0.25
    çļĦæŶéĹ´
    -0.25
     Time
    -0.25
    åľ¨ç¶²
    -0.24
    acobian
    -0.24
    otics
    -0.24
     PhpStorm
    -0.24
    mainwindow
    -0.24
    POSITIVE LOGITS
     day
    0.43
     year
    0.37
    -day
    0.35
    æĹ¥åŃIJ
    0.33
    (day
    0.33
     Day
    0.32
    	day
    0.31
    _day
    0.31
    day
    0.30
    Day
    0.30
    Activations Density 0.004%

    No Known Activations