© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8764
    Prev
    Next
    INDEX
    Explanations

    little time left

    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
    åºĵ
    -0.09
    è¡Įæĥħ
    -0.09
    èĤļ
    -0.09
    _PENDING
    -0.08
    _NPC
    -0.08
    太åŃIJ
    -0.08
    ä¸ŃæľŁ
    -0.08
    éĢį
    -0.08
    åı¸
    -0.08
     Bas
    -0.08
    POSITIVE LOGITS
    ä¸įå¾Ĺä¸į
    0.12
    没æľīåĬŀæ³ķ
    0.11
    没åĬŀæ³ķ
    0.10
    ä¸įå¾Ĺå·²
    0.10
    ä¸į容
    0.09
    è¿«
    0.09
    åıªå¾Ĺ
    0.09
    åıªèĥ½
    0.09
    åĬŀæ³ķ
    0.09
    æĹłå¥Ī
    0.09
    Activations Density 0.023%

    No Known Activations