© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51797
    Prev
    Next
    INDEX
    Explanations

    thanks and you

    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
    è¦ģç´§
    -0.09
    eses
    -0.09
    æ¸ħæĺİ
    -0.09
    æŀģåħ·
    -0.09
    没è§ģè¿ĩ
    -0.09
    çºł
    -0.09
    èĩªå·±åĸľæ¬¢
    -0.09
    Gay
    -0.09
    ç¡Ģ
    -0.09
    ãģĦãģĭ
    -0.09
    POSITIVE LOGITS
    ÑĤиÑĢов
    0.09
    isl
    0.09
    пиÑģан
    0.09
     quot
    0.09
    nos
    0.09
    çħ
    0.08
    INCLUDED
    0.08
    åĨĽ
    0.08
    é£İ鼨
    0.08
    çļĦä¿¡ä»»
    0.08
    Activations Density 0.021%

    No Known Activations