© 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. 63292
    Prev
    Next
    INDEX
    Explanations

    city 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
    izens
    -0.10
    åı£å²¸
    -0.09
    计
    -0.09
    æĭ±
    -0.09
    èij±
    -0.09
    iron
    -0.08
     Pearce
    -0.08
    ิà¸ĩ
    -0.08
    æ¡¥
    -0.08
    ossal
    -0.08
    POSITIVE LOGITS
    ä¸ŃåİŁ
    0.10
    éĴĪ对æĢ§
    0.09
    prot
    0.09
    éĥĩ
    0.08
    ä¹IJåĻ¨
    0.08
     Mort
    0.08
    鹿
    0.08
    é£İ湿
    0.08
    仪表
    0.08
    æ©Ħæ¦Ħ
    0.08
    Activations Density 0.031%

    No Known Activations