© 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. 87902
    Prev
    Next
    INDEX
    Explanations

    programming, math notation

    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
    neck
    -0.28
    è§ĦåĪĴ建设
    -0.24
     jspb
    -0.24
     OMIT
    -0.24
    ä¾µ
    -0.24
     dracon
    -0.23
    ics
    -0.23
    éķĬ
    -0.23
    conds
    -0.23
    æĪĺçķ¥æĢ§
    -0.23
    POSITIVE LOGITS
    ç»ĵ
    0.28
    owe
    0.26
    ç±ģ
    0.25
    æ´¾
    0.25
    aisy
    0.25
    å±Ģ
    0.25
     hierarchical
    0.24
    feit
    0.24
    miss
    0.24
     missed
    0.23
    Activations Density 0.009%

    No Known Activations