© 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. 5220
    Prev
    Next
    INDEX
    Explanations

    not always

    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
    å¤ĩ
    -0.10
    illus
    -0.09
    æĽ´é«ĺçļĦ
    -0.09
    æIJ¦
    -0.09
    å¤ĩæ¡Ī
    -0.09
    æĽ´é«ĺ
    -0.09
    æĻºåķĨ
    -0.08
    olan
    -0.08
    çļĦ人çĶŁ
    -0.08
    åĩºåİ»
    -0.08
    POSITIVE LOGITS
    èī°è¾Ľ
    0.09
    éłĨ
    0.09
    éļ¾åº¦
    0.09
    ä¹Łä¸įæĺ¯
    0.08
    å»ī
    0.08
    å¿ĥæĥ³
    0.08
    ä¸įå¿ĺ
    0.08
    ä¸įåħį
    0.08
     occasionally
    0.08
    _bases
    0.08
    Activations Density 0.035%

    No Known Activations