© 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. 22455
    Prev
    Next
    INDEX
    Explanations

    place names followed by descriptions

    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
    æ³ĸ
    -0.09
    å°ĨæĪIJ为
    -0.09
    .hxx
    -0.09
    æ¹ĸåĮº
    -0.08
    æľ¨èĢ³
    -0.08
    èĢģ乡
    -0.08
    ç¾¤å²Ľ
    -0.08
    æī©æķ£
    -0.08
    ä¸¤åľ°
    -0.08
    å²³éĺ³
    -0.08
    POSITIVE LOGITS
    çī¹æľīçļĦ
    0.10
    çĭ¬æľīçļĦ
    0.09
    rouw
    0.09
    åĶ¯ä¸ĢçļĦ
    0.09
    羣æŃ£çļĦ
    0.09
    è¬Ĥ
    0.09
    æľīåIJįçļĦ
    0.08
    åħ¥åı£
    0.08
    æľĢç¾İçļĦ
    0.08
    lec
    0.08
    Activations Density 0.264%

    No Known Activations