© 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. 87571
    Prev
    Next
    INDEX
    Explanations

    code 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
    ..↵↵↵↵
    -0.28
     assignable
    -0.25
    -0.25
     ideal
    -0.25
    -watch
    -0.25
     directly
    -0.24
     associate
    -0.24
     stake
    -0.24
     NI
    -0.23
     even
    -0.23
    POSITIVE LOGITS
    åĴĮæĬĢæľ¯
    0.27
    åıĬãģ³
    0.26
    åĴĮæĶ¯æĮģ
    0.25
    åĴĮå®ĮåĸĦ
    0.25
    à¹ģละà¸Ħวาม
    0.25
    à¹ģละ
    0.24
    mere
    0.24
    åĴĮæľįåĬ¡
    0.24
    ándose
    0.23
    دÙĪ
    0.23
    Activations Density 0.002%

    No Known Activations