© 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. 32238
    Prev
    Next
    INDEX
    Explanations

    Indian place 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
    èĤ¡æĿĥæĬķèµĦ
    -0.12
    ç²²
    -0.11
    èİŀ
    -0.10
    æ¯Ķäºļ
    -0.10
    æĬ¬å¤´
    -0.09
    æĤ»
    -0.09
    åħļæĢ»
    -0.09
    躬
    -0.09
    æ©IJ
    -0.09
    ä¸įå¤ļ
    -0.09
    POSITIVE LOGITS
    PM
    0.08
    uta
    0.08
    agna
    0.08
    cko
    0.08
    çŃīåľ°
    0.08
    ä¸Ģ大
    0.08
    çł´æįŁ
    0.08
    æ´Ĺ
    0.07
     alias
    0.07
    pector
    0.07
    Activations Density 0.041%

    No Known Activations