© 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. 57690
    Prev
    Next
    INDEX
    Explanations

    events and parties

    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
    èĬĴ
    -0.10
    AndView
    -0.09
    èī²æ³½
    -0.09
    转弯
    -0.09
    æĺİæľĿ
    -0.08
    imos
    -0.08
    æĬķåħ¥åĪ°
    -0.08
    å¬ĸ
    -0.08
    är
    -0.08
    uts
    -0.08
    POSITIVE LOGITS
    次æķ°
    0.12
    ç»ĵæĿŁåIJİ
    0.12
    æ°Ķæ°Ľ
    0.11
    åľºæīĢ
    0.11
    åľ°çĤ¹
    0.11
    çŃĸåĪĴ
    0.11
    ä¸Ģ次
    0.10
    æļ¨
    0.09
    åľºåIJĪ
    0.09
     sırasında
    0.09
    Activations Density 0.121%

    No Known Activations