© 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. 51391
    Prev
    Next
    INDEX
    Explanations

    banking services

    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
    çĪ°
    -0.09
     Conc
    -0.09
    éħ¬
    -0.09
    ä¸ĢçĤ¹ä¹Łä¸į
    -0.09
    ä¸ĬæĿ¥
    -0.09
     Cum
    -0.08
    ç³Ĭæ¶Ĥ
    -0.08
    æł¼
    -0.08
    éĶ¥
    -0.08
     Lump
    -0.08
    POSITIVE LOGITS
    æ³°å®ī
    0.10
    åį°åº¦
    0.10
     Pune
    0.10
     Indians
    0.09
    India
    0.09
     Delhi
    0.09
     Vig
    0.09
    æĢ»çIJĨ
    0.09
    Indian
    0.09
    ãĤ¤ãĥ³ãĥī
    0.09
    Activations Density 0.207%

    No Known Activations