© 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. 3270
    Prev
    Next
    INDEX
    Explanations

    honoured at dinner or ceremony

    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
    çĹĽ
    -0.10
    _SUS
    -0.09
    èµĽåIJİ
    -0.08
    æķ¬è¯·
    -0.08
    éĢŁ
    -0.08
    å¾Īæľī
    -0.08
    ÙħÙĪ
    -0.08
    _LVL
    -0.08
    cher
    -0.08
    	Con
    -0.08
    POSITIVE LOGITS
    à¸Ħà¸Ń
    0.10
    秦çļĩ
    0.10
    äºĨ解
    0.09
     lut
    0.09
    /owl
    0.09
    /span
    0.09
    ä¸Ĭåįĥ
    0.08
    éŨåºĹ
    0.08
     Fot
    0.08
     BAT
    0.08
    Activations Density 0.068%

    No Known Activations