© 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. 20-TRANSCODER-HP
    7. 63344
    Prev
    Next
    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĮ·
    -0.27
    ãģľ
    -0.26
     uncon
    -0.26
    åĮĢ
    -0.25
     lor
    -0.25
     breath
    -0.24
     refund
    -0.23
    çļĦä¿¡å¿ĥ
    -0.23
    _pol
    -0.23
     Nose
    -0.23
    POSITIVE LOGITS
    éĵ¯
    0.26
    apia
    0.26
    rack
    0.26
    æĬij
    0.26
    voke
    0.26
    追踪
    0.25
    emin
    0.25
    è°Ī
    0.24
    èĻ½è¯´
    0.24
    -follow
    0.24
    Activations Density 14.062%

    No Known Activations