© 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. 39163
    Prev
    Next
    INDEX
    Explanations

    tightening, tubing, spectrum, invention

    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
    ç¬ĭ
    -0.10
    æĮ¨
    -0.10
     compos
    -0.09
    lek
    -0.09
    peri
    -0.09
     Lif
    -0.09
    æĢł
    -0.09
    uil
    -0.08
    ugi
    -0.08
    å±±åĮº
    -0.08
    POSITIVE LOGITS
    è¿ĺä¸įæĺ¯
    0.09
    æ©¡èĥ¶
    0.09
    ç»·
    0.09
    æłĩçļĦ
    0.09
    æĻ®
    0.08
    çķĻç»Ļ
    0.08
    ç»į
    0.08
    æī§
    0.08
    åľĪåŃIJ
    0.08
    çĸ®
    0.08
    Activations Density 0.034%

    No Known Activations