© 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. 17950
    Prev
    Next
    INDEX
    Explanations

    times and occasions

    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
    è´¯
    -0.10
    çľĭä¸įåĩº
    -0.10
    弧
    -0.09
    åŃº
    -0.09
     Rupert
    -0.09
    貫
    -0.09
    (pg
    -0.08
    ellij
    -0.08
    çĪ·
    -0.08
    åij±
    -0.08
    POSITIVE LOGITS
    åĩłæ¬¡
    0.13
     occasions
    0.13
    æĪIJåĬŁçļĦ
    0.12
    å¤ļ次
    0.11
    两次
    0.11
     occasion
    0.11
    ä¸ī次
    0.11
    åľºåIJĪ
    0.10
    æĪIJåĬŁ
    0.10
    次æķ°
    0.10
    Activations Density 0.236%

    No Known Activations