© 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. 32907
    Prev
    Next
    INDEX
    Explanations

    words ending in "ally" before town 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
    åĪ¶åº¦æĶ¹éĿ©
    -0.10
    åѦä¼ļ
    -0.09
    isas
    -0.09
    unda
    -0.09
    è¡·
    -0.09
    ÑģÑĥд
    -0.09
    oric
    -0.08
    loom
    -0.08
     воÑĤ
    -0.08
    æ£Ĵ
    -0.08
    POSITIVE LOGITS
    æĪijèĥ½
    0.10
     Fowler
    0.10
     ÑģоÑģÑĤ
    0.09
    å°¼æĸ¯
    0.08
    ju
    0.08
     Roose
    0.08
    æ·®
    0.08
    翻身
    0.08
    OPY
    0.08
     Meet
    0.08
    Activations Density 0.010%

    No Known Activations