© 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. 56623
    Prev
    Next
    INDEX
    Explanations

    water

    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
    sono
    -0.28
    pp
    -0.26
    èĵij
    -0.25
    -btn
    -0.24
     McCart
    -0.24
    fé
    -0.24
    åĢį
    -0.24
    elyn
    -0.23
    .getHeader
    -0.23
    PRS
    -0.23
    POSITIVE LOGITS
     waters
    0.70
     water
    0.70
    æ°´åŁŁ
    0.66
    æ°´
    0.63
    æ°´ä¸Ń
    0.60
    河水
    0.59
    æµ·æ°´
    0.59
     Waters
    0.58
    water
    0.56
     водÑĭ
    0.56
    Activations Density 0.015%

    No Known Activations