© 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. 24-TRANSCODER-HP
    7. 150144
    Prev
    Next
    INDEX
    Explanations

    code/internet discussions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    relative
    -0.30
    logg
    -0.27
    utoff
    -0.26
    (relative
    -0.25
    使åij½æĦŁ
    -0.25
    å¾Īå¤ļäºĭæĥħ
    -0.25
    Quality
    -0.24
    spd
    -0.23
    mission
    -0.23
    quality
    -0.23
    POSITIVE LOGITS
    æ§Ĭ
    0.30
    æľīçĶ¨
    0.30
    éĽĨåĽ¢èĤ¡ä»½
    0.27
    æľīçĶ¨çļĦ
    0.26
    arra
    0.26
    plx
    0.25
    åħļåĴĮ
    0.25
    iano
    0.25
    gars
    0.24
    cá
    0.24
    Activations Density 0.966%

    No Known Activations