© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 89080
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guilty
    -0.29
    说çļĦè¯Ŀ
    -0.27
     oct
    -0.26
    "display
    -0.25
    _invoke
    -0.24
    æĥ³åİ»
    -0.23
     окÑĢÑĥг
    -0.23
     ÙĨÙĬÙĪز
    -0.23
    éŃĤ
    -0.23
     wouldn
    -0.23
    POSITIVE LOGITS
    parated
    0.27
    yleft
    0.26
    åĩºéŨ
    0.26
    ä½Ĩå®ĥ
    0.25
     flavored
    0.25
    utzt
    0.25
    éĥ½ä¸įæĺ¯
    0.25
    èįļ
    0.25
     Guide
    0.25
    plusplus
    0.25
    Activations Density 7.115%

    No Known Activations