© 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. 98032
    Prev
    Next
    INDEX
    Explanations

    ense

    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
    립
    -0.33
    rc
    -0.28
    TypeDef
    -0.26
    gin
    -0.26
    inion
    -0.26
    ä¸Ńå¤ĸ
    -0.26
    ä¸ĸçķĮçļĦ
    -0.24
    -dialog
    -0.24
    å¤į
    -0.24
    context
    -0.24
    POSITIVE LOGITS
    éĶĻäºĨ
    0.28
    ç«£
    0.27
     behaviour
    0.26
    _Static
    0.26
    eda
    0.26
     backing
    0.25
    CCCCCC
    0.25
     Geb
    0.25
     sos
    0.25
    missing
    0.25
    Activations Density 0.001%

    No Known Activations