© 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. 21590
    Prev
    Next
    INDEX
    Explanations

    through

    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
    è¾ħ
    -0.10
    åIJ
    -0.10
    æĪ¾
    -0.09
    çģµæ°Ķ
    -0.09
    èĽŃ
    -0.09
    åķĥ
    -0.09
    饱
    -0.09
    rell
    -0.09
    åľ¨æ·±åľ³
    -0.08
    âĸ¹
    -0.08
    POSITIVE LOGITS
    ä¾ĭè¡Į
    0.09
    æŃ£åľ¨è¿Ľè¡Į
    0.09
    æŃ£è§Ħ
    0.09
    æ´»
    0.09
    igos
    0.08
    coded
    0.08
    arity
    0.08
    éŨæĪ·
    0.08
    é«ĺå°Ķ
    0.08
    urray
    0.08
    Activations Density 0.042%

    No Known Activations