© 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. 18454
    Prev
    Next
    INDEX
    Explanations

    blood meal she

    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
    olla
    -0.10
     Archie
    -0.09
    arten
    -0.09
    è¡ĮæĶ¿
    -0.09
    æĸĩåĮĸåĴĮ
    -0.08
    æ¿
    -0.08
    ç²¹
    -0.08
    æī§æķĻ
    -0.08
    DIC
    -0.08
    urgeon
    -0.08
    POSITIVE LOGITS
    åĽ¢ä¼Ļ
    0.10
    æľįå½¹
    0.09
    人çĶŁ
    0.09
    å¥Ĺé¤IJ
    0.09
    客æ°Ķ
    0.09
     cháºŃm
    0.08
    åIJĦè¡Į
    0.08
    èĦļä¸ĭ
    0.08
     cÆ°
    0.08
    ä¼ĹçĶŁ
    0.08
    Activations Density 0.175%

    No Known Activations