© 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. 47992
    Prev
    Next
    INDEX
    Explanations

    sommelier, apartment, assistant, chaperone

    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
    ढ
    -0.09
    çŃĿ
    -0.08
    è¾ħ导
    -0.08
    åºĵåŃĺ
    -0.08
    YTE
    -0.08
    管çIJĨèĢħ
    -0.08
    endo
    -0.08
    visitor
    -0.08
     Chancellor
    -0.08
    代çłģ
    -0.08
    POSITIVE LOGITS
    å«ī
    0.10
     services
    0.10
    ä¹ĭäºī
    0.10
    -issue
    0.09
    åľ¨å¤ĸ
    0.09
    第ä¸ĢçĻ¾
    0.09
    cript
    0.09
    otropic
    0.08
    adel
    0.08
    æľįåĬ¡åĮº
    0.08
    Activations Density 0.025%

    No Known Activations