© 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. 30701
    Prev
    Next
    INDEX
    Explanations

    glee, glew, squeegee, notices

    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
    æĮĤçīĮ
    -0.09
    èĤ¡æĿĥæĬķèµĦ
    -0.09
    rip
    -0.08
    çī¢åĽºæłijç«ĭ
    -0.08
    alent
    -0.08
    æł¹æį®èĩªå·±
    -0.08
    inish
    -0.08
    ames
    -0.08
    æ»ļæ»ļ
    -0.08
     Bình
    -0.08
    POSITIVE LOGITS
    erator
    0.09
    hart
    0.09
    åľ°ä¸ĭæ°´
    0.09
     Pills
    0.09
    osas
    0.09
    ÑIJ
    0.09
    æ£Ĵ
    0.09
    FTER
    0.08
    æIJĵ
    0.08
    人çī©
    0.08
    Activations Density 0.004%

    No Known Activations