© 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. 107401
    Prev
    Next
    INDEX
    Explanations

    possibility

    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
     amp
    -0.31
     excess
    -0.25
    æ³±
    -0.24
    umed
    -0.24
    AndWait
    -0.24
    held
    -0.24
    prim
    -0.24
    èĢĮæĺ¯
    -0.23
     Sor
    -0.23
    loyd
    -0.23
    POSITIVE LOGITS
    ì»
    0.27
    thew
    0.24
    otherapy
    0.24
    ikki
    0.24
    åıijçİ°èĩªå·±
    0.24
    isoft
    0.24
    xfe
    0.24
    aje
    0.24
    esen
    0.24
    çī¹å¾ģ
    0.24
    Activations Density 24.967%

    No Known Activations