© 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. 130169
    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
     ins
    -0.27
     stack
    -0.27
    mill
    -0.27
    pun
    -0.26
    ix
    -0.26
    iller
    -0.25
     alike
    -0.25
    mus
    -0.24
     ar
    -0.24
    ç¬Ķ
    -0.24
    POSITIVE LOGITS
    è¿ĻéĩĮæĺ¯
    0.30
    foon
    0.26
     Kou
    0.26
    arning
    0.26
    enary
    0.25
    è¿ĻéĩĮæľī
    0.25
    ä¼ļä¸Ĭ
    0.25
    绶
    0.25
     []).
    0.24
     Danger
    0.24
    Activations Density 2.591%

    No Known Activations

    This feature has no known activations.