© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8704
    Prev
    Next
    INDEX
    Explanations

    families and their support

    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
    æľªæĪIJ
    -0.08
     blind
    -0.08
     bask
    -0.08
    åħ¶ä»ĸçݩ家
    -0.07
    _callbacks
    -0.07
     offen
    -0.07
    aleb
    -0.07
    CEL
    -0.07
    æģķ
    -0.07
    elon
    -0.07
    POSITIVE LOGITS
    åħ·ä½ĵæĥħåĨµ
    0.10
    ToPoint
    0.10
    паÑĢ
    0.10
    åĩºæ¸¸
    0.09
    лей
    0.09
    åıĤè°ĭ
    0.09
    æĺĮ
    0.09
    \widgets
    0.09
    поÑĤ
    0.09
    .GL
    0.09
    Activations Density 0.021%

    No Known Activations