© 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. 10915
    Prev
    Next
    INDEX
    Explanations

    want to / like to

    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
    é¾Ļæ¹ĸ
    -0.10
    ç§ī
    -0.09
    åĬ¨çĶŁæĪIJ
    -0.09
    hyth
    -0.09
    lico
    -0.09
    ÙĪÙī
    -0.09
    aos
    -0.09
     Muk
    -0.09
    inition
    -0.09
    iting
    -0.09
    POSITIVE LOGITS
    èħ¹
    0.09
    æĭ±
    0.09
    äºĨä¸ĭæĿ¥
    0.08
    èľĢ
    0.08
    rd
    0.08
     adel
    0.08
    ç¡®å®ŀ
    0.08
    æŁIJä¸Ģ
    0.08
    ropol
    0.08
    å°±åı¯ä»¥
    0.08
    Activations Density 0.037%

    No Known Activations