© 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. 23787
    Prev
    Next
    INDEX
    Explanations

    .com

    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
    æĶ»
    -0.28
    åıĺå½¢
    -0.25
     fict
    -0.24
    æĩ¿
    -0.24
    ä¸įå¿į
    -0.24
    pairs
    -0.24
    Soup
    -0.24
    áĥ¦
    -0.23
    æĶ»æīĵ
    -0.23
    å¾Ī容æĺĵ
    -0.23
    POSITIVE LOGITS
    çĶ¬
    0.27
    unger
    0.25
    quam
    0.25
    CJK
    0.25
    æıIJä¾Ľä¼ĺè´¨
    0.24
    exus
    0.24
    ìłij
    0.23
    untu
    0.23
    Bas
    0.23
    apsible
    0.23
    Activations Density 0.001%

    No Known Activations