© 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. 1115
    Prev
    Next
    INDEX
    Explanations

    Strauss and variations

    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
    å³Ĵ
    -0.09
    owing
    -0.09
    çĽ¼æľĽ
    -0.08
    lug
    -0.08
    ä¸ĸçķĮä¸ĬæľĢ
    -0.08
    ìĤ¬íķŃ
    -0.08
     rÃłng
    -0.08
    忱
    -0.08
    褰
    -0.08
    寺
    -0.08
    POSITIVE LOGITS
    kop
    0.10
    eln
    0.09
    ì±ħ
    0.09
    pped
    0.09
    ä»Ħ
    0.08
    Ñĥни
    0.08
    encies
    0.08
    eur
    0.08
    flight
    0.08
    ipt
    0.08
    Activations Density 0.012%

    No Known Activations