© 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. 12-TRANSCODER-HP
    7. 23634
    Prev
    Next
    INDEX
    Explanations

    Universal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    主
    -0.27
    iteDatabase
    -0.27
    amental
    -0.26
    endra
    -0.26
    .bs
    -0.25
    Disclosure
    -0.25
     vals
    -0.25
    ys
    -0.25
    main
    -0.25
    åŁ
    -0.25
    POSITIVE LOGITS
    æĽ´å¤§çļĦ
    0.28
     ^=
    0.27
    ä¸įåıĬ
    0.26
    è¿Ļ个æŶåĢĻ
    0.26
    ptime
    0.26
    æµ£
    0.26
    çŃīåĽłç´ł
    0.26
    #__
    0.26
    为æ°ij
    0.25
    ppv
    0.25
    Activations Density 0.052%

    No Known Activations