© 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. 54722
    Prev
    Next
    INDEX
    Explanations

    president of

    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
    uch
    -0.09
    undler
    -0.09
    çķĻç»Ļ
    -0.09
    æĹłæīĢ
    -0.09
    认è´Ń
    -0.09
    ç¬ij声
    -0.08
    èĹIJ
    -0.08
    asper
    -0.08
    Jur
    -0.08
    _bm
    -0.08
    POSITIVE LOGITS
    åIJİæĤĶ
    0.09
    æĥĭ
    0.08
    åĬŃ
    0.08
    UA
    0.08
    åįĹå±±
    0.08
    çĥı
    0.08
    ä¼ĺ
    0.08
    çIJ¬
    0.08
    éĿ¶
    0.08
    ä»Ģä¹Īåij¢
    0.08
    Activations Density 0.041%

    No Known Activations