© 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. 3263
    Prev
    Next
    INDEX
    Explanations

    over whether

    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
    agli
    -0.10
    íĭ°
    -0.10
    éĿ¢å¯¹
    -0.10
    è°Īè°Ī
    -0.09
    æĥħåĨµä¸ĭ
    -0.09
    oter
    -0.09
    زÙĦ
    -0.09
    åĩ¡äºĭ
    -0.09
    FRING
    -0.09
    çĶ¨äºİ
    -0.09
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.10
    éĢŀ
    0.09
    èĦļä¸ĭ
    0.09
     lẽ
    0.08
    åħ±åIJĮåıijå±ķ
    0.08
     whether
    0.08
    è¿ĻçĤ¹
    0.08
    eks
    0.08
    è¦ģä¸įè¦ģ
    0.08
    åīįè¾Ī
    0.08
    Activations Density 0.155%

    No Known Activations