© 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. 150381
    Prev
    Next
    INDEX
    Explanations

    giving or doing something

    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
     subj
    -0.28
    为åħ¶
    -0.27
    subj
    -0.27
    æĿ¥åģļ
    -0.26
    åĵİ
    -0.25
     sense
    -0.25
    ä¹Łä¸įçŁ¥éģĵ
    -0.24
    è¦ģ害
    -0.24
    ç²³
    -0.24
    identally
    -0.24
    POSITIVE LOGITS
    -in
    0.26
    å¤ļ次
    0.26
    çļĦæĥħåĨµ
    0.25
     dav
    0.24
    iners
    0.24
    çļĦæĥħå½¢
    0.24
    icy
    0.24
    uces
    0.24
    ngo
    0.23
    ////////////////////////////////////////////////////////////////////
    0.23
    Activations Density 0.969%

    No Known Activations