© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7185
    Prev
    Next
    INDEX
    Explanations

    was or has

    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
    带ç»Ļ
    -0.08
    éģ½
    -0.08
    èĩªåѦ
    -0.08
    æľīåı¯èĥ½
    -0.08
    çŀŃ
    -0.08
    è¿Ī
    -0.08
    preneur
    -0.08
    udge
    -0.07
    太太
    -0.07
    ity
    -0.07
    POSITIVE LOGITS
    æľįåĬ¡äºİ
    0.11
    æĥ¯
    0.10
    æīĭ段
    0.10
    åı£å¾Ħ
    0.10
    æ¸ĹéĢı
    0.10
    åħ¨æĸ¹ä½į
    0.09
    èŁ
    0.09
    .Skin
    0.09
    æĬĵ
    0.09
    åIJİåı°
    0.09
    Activations Density 0.095%

    No Known Activations