© 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. 63614
    Prev
    Next
    INDEX
    Explanations

    Numerical digits

    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
     pháp
    -0.28
    ag
    -0.27
    åѦåĪ°
    -0.24
    жение
    -0.24
    ç¼°
    -0.23
    unately
    -0.23
    éķĸ
    -0.23
    ä½ľèĢħæľ¬äºº
    -0.23
    åĿŀ
    -0.23
     claimed
    -0.22
    POSITIVE LOGITS
    enie
    0.26
    æĪĸå¤ļ
    0.25
    THREAD
    0.25
    çIJĩ
    0.24
    Ñıн
    0.24
    ETY
    0.24
    urch
    0.23
    对åŃ©åŃIJ
    0.23
    çĩ§
    0.23
    éľ¾
    0.23
    Activations Density 8.567%

    No Known Activations