© 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. 141403
    Prev
    Next
    INDEX
    Explanations

    foods

    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
    lü
    -0.26
    羯
    -0.26
    inium
    -0.26
     обÑĢазом
    -0.25
    olley
    -0.25
    icipation
    -0.24
    sites
    -0.24
    icamente
    -0.24
    aire
    -0.24
    è¿Ļç§įæĸ¹æ³ķ
    -0.24
    POSITIVE LOGITS
    ansom
    0.30
     refr
    0.29
     beats
    0.26
     like
    0.26
    quo
    0.26
    é£İéĻ©
    0.24
    å±Ĭ
    0.24
    éĤ£ä¸ªæŶåĢĻ
    0.24
     mass
    0.24
    æĹ¥åŃIJ
    0.24
    Activations Density 11.345%

    No Known Activations