© 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. 21962
    Prev
    Next
    INDEX
    Explanations

    small towns and villages

    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
    OST
    -0.10
    æ°ª
    -0.09
    åijĹ
    -0.09
    åħ¨éĿ¢åıijå±ķ
    -0.09
    éĩįçĶŁ
    -0.09
    æĥ³æī¾
    -0.09
    éĤij
    -0.08
    æŁ¿
    -0.08
    èį¡
    -0.08
     yazılı
    -0.08
    POSITIVE LOGITS
    ä½įäºİ
    0.11
     suburb
    0.10
    éļ¶å±ŀäºİ
    0.09
    æĸĻ
    0.09
    REEN
    0.09
    æĸ¹åľĨ
    0.09
    è·Ŀ离
    0.08
    ewhere
    0.08
    ç³ĸå°¿
    0.08
    å¿«è¦ģ
    0.08
    Activations Density 0.197%

    No Known Activations