© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37689
    Prev
    Next
    INDEX
    Explanations

    units of distance, time, and area

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heet
    -0.09
    åıªæľīä¸Ģ个
    -0.09
    sense
    -0.09
    çļĦæĸ¹åIJij
    -0.09
    sar
    -0.09
    scheduler
    -0.08
    以èī²
    -0.08
    è¶Ĭè¿ĩ
    -0.08
    iciones
    -0.08
    eday
    -0.08
    POSITIVE LOGITS
    swith
    0.11
    sthrough
    0.11
    ss
    0.09
    unks
    0.09
    ees
    0.09
    ãģĵãģ¨
    0.09
    sWith
    0.08
    enu
    0.08
    orsi
    0.08
    idy
    0.08
    Activations Density 0.101%

    No Known Activations