© 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. 26830
    Prev
    Next
    INDEX
    Explanations

    cave, frostbite, swimming performance, Bed Bugs, olive-shaped

    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
    æ¶ī
    -0.08
    诩
    -0.08
    irim
    -0.08
    å¿ĥæĢĿ
    -0.08
    åķĸ
    -0.08
    ä»ħ次äºİ
    -0.08
    èĮ«èĮ«
    -0.08
     ÑĢаÑģÑĩеÑĤ
    -0.08
    ront
    -0.08
     plata
    -0.08
    POSITIVE LOGITS
    æ¼ī
    0.10
    æ¯Ķäºļ
    0.09
    åĪĽæĸ°èĥ½åĬĽ
    0.09
    åħ¥åı£
    0.08
    æĶ¾å¿ĥ
    0.08
    å°´å°¬
    0.08
    åĮĢ
    0.08
    æĬ¤çħ§
    0.08
    oled
    0.08
     Tattoo
    0.08
    Activations Density 0.211%

    No Known Activations