© 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. 4037
    Prev
    Next
    INDEX
    Explanations

    fictional cyborgs and robots

    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
    æ°ijèѦ
    -0.09
    eid
    -0.09
    خد
    -0.08
    /download
    -0.08
    ival
    -0.08
     distract
    -0.08
    fare
    -0.08
     Fant
    -0.08
    äºĴèģĶ
    -0.08
    éĹ»
    -0.08
    POSITIVE LOGITS
    åĩºçİ°åľ¨
    0.09
     spear
    0.09
    èµŁ
    0.09
    约ä¼ļ
    0.09
    æľīä¿¡å¿ĥ
    0.09
    éĿłè°±
    0.08
    çĥģ
    0.08
    女人
    0.08
    纪
    0.08
    çĽ¯
    0.08
    Activations Density 0.007%

    No Known Activations