© 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. 22796
    Prev
    Next
    INDEX
    Explanations

    detecting or knowing status

    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
    大家ä¸Ģèµ·
    -0.10
    æıIJåĩº
    -0.09
    åĽłä¸ºæĪij
    -0.09
    çĽ¸ä¿¡å¤§å®¶
    -0.09
    åĽłä¸ºæĪij们
    -0.09
    IME
    -0.09
    çķ¹
    -0.09
    åIJ¹
    -0.08
    æ¶Īè´¹
    -0.08
    _GU
    -0.08
    POSITIVE LOGITS
    ä½ķæŶ
    0.11
    è¯ĨåĪ«
    0.10
    å¹¶åľ¨
    0.09
    çĵ£
    0.09
    å°±è¶Ĭ
    0.09
    æ¼Ĩ
    0.09
     налиÑĩие
    0.09
    nowledge
    0.09
    侦
    0.09
     налиÑĩ
    0.09
    Activations Density 0.300%

    No Known Activations