© 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. 6789
    Prev
    Next
    INDEX
    Explanations

    say, says, said followed by words

    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
    çIJĨæĥ³çļĦ
    -0.09
    _ten
    -0.08
    .createObject
    -0.08
    èĦ±
    -0.08
    èµĬ
    -0.08
    ãģĻ
    -0.08
     shoe
    -0.08
    æıĨ
    -0.08
     whatsoever
    -0.08
    ä¸įä½ı
    -0.08
    POSITIVE LOGITS
    èĩªå·±
    0.12
    说èĩªå·±
    0.11
    è§īå¾Ĺèĩªå·±
    0.11
    æĦŁè§īèĩªå·±
    0.10
    声称
    0.10
    åıijçİ°èĩªå·±
    0.10
    èĩªå·±çļĦ
    0.09
    icky
    0.09
     mình
    0.09
    读æĩĤ
    0.09
    Activations Density 0.118%

    No Known Activations