© 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. 63929
    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
    basis
    -0.32
     basis
    -0.31
     ring
    -0.28
     crib
    -0.28
    RING
    -0.26
    _ring
    -0.24
    æ°´æµģ
    -0.24
     Ri
    -0.24
    wed
    -0.24
    ption
    -0.24
    POSITIVE LOGITS
    olute
    0.29
     Garr
    0.28
    aget
    0.27
    ogl
    0.27
    æĹłæķĮ
    0.26
    ä»Ģä¹ĪæŶåĢĻ
    0.26
    icz
    0.25
    ÑĤÑĮ
    0.25
    lich
    0.24
    egl
    0.24
    Activations Density 5.468%

    No Known Activations

    This feature has no known activations.