© 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. 20617
    Prev
    Next
    INDEX
    Explanations

    already known and suspected

    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
    lemn
    -0.10
    æŃ¦å£«
    -0.10
    kaar
    -0.09
    :`~
    -0.09
    大å¸Ī
    -0.09
    otics
    -0.08
    _hooks
    -0.08
    ä¸ĢæľŁ
    -0.08
    æ¯ĸ
    -0.08
    è¿IJ
    -0.08
    POSITIVE LOGITS
    æĹ©å·²
    0.15
    æĹ©å°±
    0.13
     already
    0.11
    already
    0.11
    ä¸Ģ缴éĥ½
    0.11
    å·²çĦ¶
    0.10
     давно
    0.10
    éĥ¨åĪĨåĨħ容
    0.10
    å·²ä¹ħçļĦ
    0.09
    å·²äºİ
    0.09
    Activations Density 0.062%

    No Known Activations