© 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. 111904
    Prev
    Next
    INDEX
    Explanations

    Random text 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
     OE
    -0.27
    lli
    -0.26
     testify
    -0.26
    lyph
    -0.25
     //=
    -0.25
    åį
    -0.24
     Nights
    -0.24
    åİ®
    -0.24
    inel
    -0.24
    æ¶Ķ
    -0.24
    POSITIVE LOGITS
    åĪĨ为
    0.52
    ä¸įåIJĮçļĦ
    0.49
     different
    0.45
    åIJĦ个
    0.45
    åĪĨåĪ«
    0.45
    ä¸įåIJĮ
    0.44
    ãģĿãĤĮãģŀãĤĮ
    0.43
    åĪĨç±»
    0.43
    ä¸įåIJĮç±»åŀĭ
    0.43
     either
    0.41
    Activations Density 0.004%

    No Known Activations