© 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. 19156
    Prev
    Next
    INDEX
    Explanations

    purpose

    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
    çĶļèĩ³
    -0.10
    çĶļèĩ³æĺ¯
    -0.10
    ạp
    -0.08
    主æµģ
    -0.08
    æĦŁ
    -0.07
    åĵªæĢķ
    -0.07
    اث
    -0.07
    qua
    -0.07
    åıĪèĥ½
    -0.07
    OWL
    -0.07
    POSITIVE LOGITS
    è¿ĻåIJį
    0.13
    æĺİçĻ½äºĨ
    0.10
    æ¦Ĥè¿°
    0.10
    å®ĹæŨ
    0.10
    缮çļĦæĺ¯
    0.10
    管çIJĨæĿ¡ä¾ĭ
    0.10
    åĪĨå·¥
    0.09
    éĻĪè¿°
    0.09
     purpose
    0.09
    íħIJ
    0.09
    Activations Density 0.128%

    No Known Activations