© 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. 32-TRANSCODER-HP
    7. 43190
    Prev
    Next
    INDEX
    Explanations

    spatiotemporal patterns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     time
    -0.81
    æŶéĹ´
    -0.77
    time
    -0.65
     Time
    -0.63
    çļĦæŶéĹ´
    -0.63
    _time
    -0.63
    æĻĤéĸĵ
    -0.62
    Time
    -0.59
    æŶéĹ´åĴĮ
    -0.55
    	time
    -0.54
    POSITIVE LOGITS
    ary
    0.27
    ARY
    0.25
    SG
    0.25
    ate
    0.25
    åĮ»ç§ij大åѦ
    0.25
    éĿł
    0.25
    åı¯ä»¥èİ·å¾Ĺ
    0.24
    ada
    0.23
    oler
    0.23
    attern
    0.23
    Activations Density 0.003%

    No Known Activations