© 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. 35801
    Prev
    Next
    INDEX
    Explanations

    music names

    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
     Hairst
    -0.10
    ä¸įçŁ¥
    -0.09
    æ´¹
    -0.09
    ERVE
    -0.09
    éĺ
    -0.09
    ihan
    -0.08
    æĮ£æīİ
    -0.08
     Ñģоб
    -0.08
    顺德
    -0.08
    åľ°æ®µ
    -0.08
    POSITIVE LOGITS
    èł¹
    0.10
    éħĴä¸ļ
    0.09
    ething
    0.09
     bbc
    0.09
    æį©
    0.08
    isu
    0.08
    æºŁ
    0.08
    irl
    0.08
    åĢĻ
    0.08
    è§Ħ模æľĢ大
    0.08
    Activations Density 0.003%

    No Known Activations