© 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. 7875
    Prev
    Next
    INDEX
    Explanations

    Still or inactive

    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
    Negative Logits
    pillar
    -0.29
    categoryId
    -0.27
    Rating
    -0.27
    aptive
    -0.27
    acular
    -0.25
    RI
    -0.25
     Shelf
    -0.24
     ControllerBase
    -0.24
    è¿ĺä¸įå¦Ĥ
    -0.24
    åĩºå¤Ħ
    -0.24
    POSITIVE LOGITS
    æ°´åĪĨ
    0.30
     water
    0.29
     sunlight
    0.28
    UNCH
    0.26
    angan
    0.26
    Proto
    0.26
    饿
    0.26
    æĢİä¹Īçľĭ
    0.25
    ewater
    0.25
    )))),
    0.25
    Activations Density 0.009%

    No Known Activations