© 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. 54848
    Prev
    Next
    INDEX
    Explanations

    spontaneous, impulsive, improvisation, on the fly

    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
    èijĨ
    -0.10
    etz
    -0.10
     Pend
    -0.09
    ç¬ijç¬ij
    -0.09
    åıĮåIJij
    -0.09
    å½ĵ代
    -0.09
    æĻĵå¾Ĺ
    -0.09
    åħļ
    -0.09
    ammen
    -0.09
    è¸ıåħ¥
    -0.08
    POSITIVE LOGITS
    临æŶ
    0.16
     spont
    0.15
    åĮĨ
    0.14
    åį³æŶ
    0.13
    èĩ¨
    0.13
    çªģåıij
    0.13
    åºĶæĢ¥
    0.13
     improvis
    0.12
    临
    0.12
    éļıæīĭ
    0.12
    Activations Density 0.087%

    No Known Activations