© 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. 54620
    Prev
    Next
    INDEX
    Explanations

    place names ending

    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
    çĶij
    -0.10
    ves
    -0.10
    ToBounds
    -0.09
    VES
    -0.09
    缶
    -0.09
    éģį
    -0.08
    ä»ĵ
    -0.08
    æīĺè¿IJ
    -0.08
    \Bridge
    -0.08
    宸
    -0.08
    POSITIVE LOGITS
    æĽ´æľī
    0.11
    æı©
    0.10
    è¿ĻçĤ¹
    0.10
    ç§ijæĬĢèĤ¡ä»½
    0.09
    kaar
    0.09
     kÃŃch
    0.09
    âĵĺ
    0.09
    çĤ¹åĦ¿
    0.09
    è°Ľ
    0.09
    кÑĢи
    0.08
    Activations Density 0.109%

    No Known Activations