© 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. 130274
    Prev
    Next
    INDEX
    Explanations

    Technical documentation snippets

    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
    ä¸įä¿¡
    -0.28
    prites
    -0.27
    ONUS
    -0.27
    _games
    -0.27
    æѤäºĭ
    -0.25
    anean
    -0.25
    onas
    -0.25
    该åī§
    -0.25
    å·±
    -0.24
     yaÅŁadıģı
    -0.24
    POSITIVE LOGITS
    主è¦ģåĮħæĭ¬
    0.39
    æľī两ç§į
    0.37
    æľĢåŁºæľ¬çļĦ
    0.36
     most
    0.36
     broadly
    0.36
    主è¦ģæľī
    0.35
    æľĢåŁºæľ¬
    0.35
     Most
    0.34
    åı¯åĪĨ为
    0.33
     commonly
    0.33
    Activations Density 0.002%

    No Known Activations