© 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. 22-TRANSCODER-HP
    7. 87415
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     generally
    -0.31
     free
    -0.29
     normally
    -0.27
     ordinarily
    -0.26
     abst
    -0.26
    ademic
    -0.26
     observ
    -0.25
     naturally
    -0.25
     regard
    -0.25
     Ih
    -0.25
    POSITIVE LOGITS
    ikt
    0.30
    æ¿ĢçĥĪ
    0.29
    åIJĦèĩªçļĦ
    0.28
    åħ¶ä»ĸ
    0.27
    è¯ŀçĶŁ
    0.27
    åIJĦèĩª
    0.27
    æīĢåľ¨
    0.27
    åĭĩ
    0.26
    è¯Ħ论
    0.25
    æľĢåIJİ
    0.25
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.