© 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. 22209
    Prev
    Next
    INDEX
    Explanations

    trial, sample, free, try, guarantee

    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
    eut
    -0.10
    ales
    -0.09
    ij
    -0.09
    Gap
    -0.08
    åıĬåħ¶
    -0.08
    æĢĽ
    -0.08
    鸦
    -0.08
    è¾ĩ
    -0.08
    æļĿ
    -0.08
    _variable
    -0.08
    POSITIVE LOGITS
    æľŁéĹ´
    0.13
    æľŁåĨħ
    0.11
    å§Ķç»Ħç»ĩ
    0.10
    ï¸ı
    0.10
    æ´»åĬ¨ä¸Ń
    0.10
    åĪĩãĤĮ
    0.09
    ä½ĵçİ°åĩº
    0.09
    è¿ĩç¨ĭä¸Ń
    0.09
    è¿ĩåIJİ
    0.09
    è¯ķè¯ķ
    0.09
    Activations Density 0.012%

    No Known Activations