© 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. 149848
    Prev
    Next
    INDEX
    Explanations

    Scientific, alcoholic, musical

    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
    天èĬ±æĿ¿
    -0.27
    ive
    -0.27
    åĮĹéĥ¨
    -0.27
    åĨł
    -0.25
    pread
    -0.25
    太é«ĺ
    -0.24
    ä¸ĢåĪĩéĥ½
    -0.24
    æį¢ä¸ª
    -0.24
     perme
    -0.24
    allen
    -0.23
    POSITIVE LOGITS
    prise
    0.28
    çIJ¨
    0.25
    olini
    0.25
    åĤħ
    0.24
     ISI
    0.24
    çŀ¬
    0.24
    bout
    0.24
    hti
    0.23
     mt
    0.23
     Soci
    0.23
    Activations Density 2.078%

    No Known Activations