© 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. 63998
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    毯
    -0.28
    (AF
    -0.25
    æŁı
    -0.25
    åĬ©æīĭ
    -0.25
    isos
    -0.25
    æĪij们éľĢè¦ģ
    -0.25
     fooled
    -0.24
    åŁºå±Ĥ
    -0.24
    ÑĢак
    -0.24
    æĴ¥
    -0.23
    POSITIVE LOGITS
    quared
    0.27
    éļį
    0.26
     Tmax
    0.25
    hud
    0.25
    olon
    0.25
    iform
    0.25
     symmetry
    0.24
     Ost
    0.24
     nominal
    0.23
    ...č↵
    0.23
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.