© 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. 63562
    Prev
    Next
    INDEX
    Explanations

    merges

    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
    æīĭåĬ¨
    -0.26
    è¡¥é½IJ
    -0.26
    ownt
    -0.25
    åĬ¨æīĭ
    -0.25
     manually
    -0.25
    %p
    -0.25
    -destruct
    -0.24
     кваÑĢ
    -0.23
    ä¸įå®ļ
    -0.23
    омеÑĢ
    -0.23
    POSITIVE LOGITS
    mons
    0.26
     Prof
    0.26
    æıIJåıĬ
    0.25
    mere
    0.25
    åĬ©
    0.25
     topLevel
    0.24
    emon
    0.24
    éĹ®æĪij
    0.24
    -scalable
    0.23
    chers
    0.23
    Activations Density 20.687%

    No Known Activations