© 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. 2412
    Prev
    Next
    INDEX
    Explanations

    attraction to

    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
     quo
    -0.09
    èĤļåŃIJ
    -0.09
    ä¸ŃåĽ½è¶³çIJĥ
    -0.09
    éģı
    -0.08
    缸å½ĵ
    -0.08
    å¿ĥæĦ¿
    -0.08
    èĥ³èĨĬ
    -0.08
    主è§Ĵ
    -0.08
    æĸ§
    -0.08
    basis
    -0.08
    POSITIVE LOGITS
    强çĥĪçļĦ
    0.10
     grav
    0.10
    çĥ
    0.09
    æĬ¥èĢĥ
    0.09
    寥
    0.09
    åĬŀ
    0.09
    大éĩıçļĦ
    0.09
    æĸ°æĬĢæľ¯
    0.09
    æħķ
    0.08
    ç»Ĥ
    0.08
    Activations Density 0.014%

    No Known Activations