© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10461
    Prev
    Next
    INDEX
    Explanations

    exciting, promising, intriguing

    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
    æĹłæĥħ
    -0.10
    ory
    -0.09
    aklı
    -0.08
    æīįç®Ĺ
    -0.08
    åĽłä¸ºä»ĸ
    -0.08
    óm
    -0.08
    å¾ĹæĦı
    -0.08
    guid
    -0.08
    ouro
    -0.08
    ä¸ĢçĤ¹éĥ½ä¸į
    -0.08
    POSITIVE LOGITS
     promising
    0.13
     promises
    0.12
     promised
    0.11
     intrig
    0.11
     intriguing
    0.10
    æĦŁè§ī
    0.10
    åIJ¬èµ·æĿ¥
    0.10
    æį®è¯´
    0.10
    ç«Łæĺ¯
    0.10
    æī¿è¯º
    0.10
    Activations Density 0.119%

    No Known Activations