© 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. 111380
    Prev
    Next
    INDEX
    Explanations

    references

    np_max-act · gemini-2.0-flash
    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
     surrounds
    -0.28
    mage
    -0.27
    تصÙģ
    -0.24
    grounds
    -0.24
    éľı
    -0.23
    تÙĦ
    -0.23
    processable
    -0.23
     Renders
    -0.23
    é£
    -0.23
    æģĴ
    -0.23
    POSITIVE LOGITS
    esen
    0.29
     naturally
    0.25
    ç¬ijç¬ij
    0.24
    åħ¶ä»ĸåĽ½å®¶
    0.24
     equally
    0.24
    æķķ
    0.23
    awah
    0.23
    èĸ¤
    0.23
     similarly
    0.23
    åĮºæĶ¿åºľ
    0.23
    Activations Density 0.002%

    No Known Activations