© 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. 64335
    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
     sut
    -0.30
    æ²Ķ
    -0.28
     need
    -0.26
    antan
    -0.26
    å°ij
    -0.26
    -sided
    -0.25
    ;font
    -0.25
    ewhere
    -0.25
    ansi
    -0.25
    èįª
    -0.25
    POSITIVE LOGITS
    odings
    0.30
    zed
    0.29
     dame
    0.28
    è¿ĩçļĦ
    0.26
    ches
    0.25
    å¤©åĽ½
    0.24
     disproportion
    0.24
    oted
    0.24
    ovation
    0.24
    ÑĥÑī
    0.24
    Activations Density 4.171%

    No Known Activations

    This feature has no known activations.