© 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. 9-TRANSCODER-HP
    7. 29703
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĭ¬ç«ĭ
    -0.31
    çį¨ç«ĭ
    -0.29
     independent
    -0.26
     independence
    -0.26
    adr
    -0.26
    æĬķ产
    -0.26
    би
    -0.25
    åłij
    -0.25
     soak
    -0.24
     edge
    -0.24
    POSITIVE LOGITS
    Lens
    0.30
     ÙĬأتÙĬ
    0.25
    åĩºäºİ
    0.25
    	End
    0.25
    æĽ
    0.25
    kits
    0.25
    çļĦä¼łç»Ł
    0.24
     Rencontres
    0.24
    hoff
    0.23
    YRO
    0.23
    Activations Density 1.047%

    No Known Activations