© 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. 4671
    Prev
    Next
    INDEX
    Explanations

    words starting with 'su', 'fe', 'pr', 'gr', 'qu', 'ne', 'dem', 'est'

    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
    èĩªæĿ¥
    -0.10
    éªijè¡Į
    -0.09
    ichi
    -0.09
    é¹Ń
    -0.09
    ä½ĥ
    -0.09
    ìļ©
    -0.09
    è¤ļ
    -0.09
    ç¿İ
    -0.09
    éĶ¦ç»£
    -0.09
    ojis
    -0.09
    POSITIVE LOGITS
    纳åħ¥
    0.08
    åľ°ä¸ĭ
    0.08
     prop
    0.08
    æĦ§
    0.07
     ore
    0.07
    _rp
    0.07
    azen
    0.07
    æĦıä¹īä¸ĬçļĦ
    0.07
    ror
    0.07
    ENSE
    0.07
    Activations Density 0.243%

    No Known Activations