© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51029
    Prev
    Next
    INDEX
    Explanations

    DNA, fiber, bone, lens

    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
    车åŃIJ
    -0.11
    åĽ½å®ī
    -0.10
    거리
    -0.10
    家ä¼Ļ
    -0.10
    åįģ足
    -0.10
    ä¹ĭä½ľ
    -0.10
    è¿ĩå¾Ĺ
    -0.09
    ä¸İåıijå±ķ
    -0.09
    åŃĺåľ¨äºİ
    -0.09
    .removeFrom
    -0.09
    POSITIVE LOGITS
    ä¸ĬçļĦ
    0.11
    éĹ´çļĦ
    0.09
    czy
    0.08
    borne
    0.08
    çļĦä¸įåIJĮ
    0.08
    ä¸Ńä¿¡
    0.08
    /mat
    0.08
    æľ¬èº«
    0.07
    lover
    0.07
    åĨħçļĦ
    0.07
    Activations Density 0.697%

    No Known Activations