© 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. 11209
    Prev
    Next
    INDEX
    Explanations

    ownership

    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
    æѤç§į
    -0.10
    onda
    -0.10
    è¿Ļ两ç§į
    -0.09
    èĩªå·±åĸľæ¬¢
    -0.09
    éĢĨ
    -0.08
    æĥĬå¥ĩ
    -0.08
    è¿Ļç§įæĥħåĨµ
    -0.08
    æ¨Ĭ
    -0.08
     Ùħؤ
    -0.08
    æľīæīĢ
    -0.08
    POSITIVE LOGITS
    ä¸įæŃ»
    0.10
     RELEASE
    0.09
    stu
    0.09
    åıijå¸ĥçļĦ
    0.09
    mor
    0.09
    å¥
    0.08
    åij¤
    0.08
    eral
    0.08
    çĵ£
    0.08
    fruit
    0.08
    Activations Density 0.024%

    No Known Activations