© 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. 23658
    Prev
    Next
    INDEX
    Explanations

    tough

    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
    é«ĺãģı
    -0.09
    æľ
    -0.09
     treÅĽci
    -0.09
    ally
    -0.08
    ç¾İ好çĶŁæ´»
    -0.08
    воÑĢ
    -0.08
    ä¸Ģå¤Ħ
    -0.08
    人大
    -0.08
    大佬
    -0.08
    éħ¬
    -0.08
    POSITIVE LOGITS
    ened
    0.17
     Tough
    0.12
    ening
    0.12
     khÄĥn
    0.12
    ord
    0.11
    -minded
    0.11
    sit
    0.10
     tough
    0.10
    ifying
    0.10
    Ñĥб
    0.10
    Activations Density 0.011%

    No Known Activations