© 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. 32485
    Prev
    Next
    INDEX
    Explanations

    bank act, nominal terms, pump for, independent agency, wheel cylinders

    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
    è¸ı
    -0.11
    edly
    -0.10
    omi
    -0.09
    ä¸ĢèĦļ
    -0.09
    åłµ
    -0.09
    åı¯ä¿¡
    -0.09
    ·æĸ°
    -0.09
    æı¡æīĭ
    -0.09
    åĬ
    -0.09
    æ´»ä¸ĭåİ»
    -0.09
    POSITIVE LOGITS
    éĺī
    0.09
    èĮ§
    0.09
     Pret
    0.09
    imag
    0.09
    éĩī
    0.08
    驼
    0.08
     Dispatch
    0.08
     lazy
    0.08
    åĺĺ
    0.08
    æŨ
    0.08
    Activations Density 0.027%

    No Known Activations