© 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. 141457
    Prev
    Next
    INDEX
    Explanations

    error

    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
    èĥ±
    -0.25
     teng
    -0.25
    第äºĮ
    -0.24
    éħļ
    -0.24
    第äºĮç§į
    -0.24
    nings
    -0.24
    rior
    -0.24
     ÑģÑĦ
    -0.24
    -redux
    -0.23
    第äºĮ次
    -0.23
    POSITIVE LOGITS
    æŦ
    0.27
    çĪ¬
    0.27
     Constit
    0.26
    trusted
    0.25
    oyo
    0.25
    举è¡Į
    0.24
     trib
    0.24
    ouve
    0.24
    çļĦåij½è¿IJ
    0.23
    æ¼ıæ´ŀ
    0.23
    Activations Density 1.209%

    No Known Activations