© 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. 8050
    Prev
    Next
    INDEX
    Explanations

    legal/scientific documents

    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
    éĩĬ
    -0.28
    ayo
    -0.28
    ToolTip
    -0.26
     wink
    -0.25
    affer
    -0.24
    stm
    -0.24
    ayers
    -0.24
     vari
    -0.24
     deposited
    -0.24
     structures
    -0.24
    POSITIVE LOGITS
    èµ°
    0.29
    åī¯ä¸»ä»»
    0.28
    ç±į
    0.27
    èµ°åİ»
    0.27
     ank
    0.26
    åī¯æĢ»
    0.26
    Prec
    0.26
     orientation
    0.26
    æķ£æŃ¥
    0.25
    haus
    0.24
    Activations Density 0.001%

    No Known Activations