© 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. 20926
    Prev
    Next
    INDEX
    Explanations

    probing molecules, signals, or communications

    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
     íĺ¸
    -0.09
    аÑĪ
    -0.09
    Į¨
    -0.09
    coming
    -0.09
    icing
    -0.09
    åĬŁåĬ³
    -0.08
    ãĤ»
    -0.08
    fol
    -0.08
    ose
    -0.08
    æIJ¬è¿IJ
    -0.08
    POSITIVE LOGITS
    ingly
    0.12
    ä¸įåĩºæĿ¥
    0.10
    è¨İ
    0.10
    anst
    0.10
    erval
    0.10
     Gaines
    0.09
    acular
    0.09
    æ´½
    0.09
    utos
    0.09
    جاÙĦ
    0.09
    Activations Density 0.021%

    No Known Activations