© 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. 19711
    Prev
    Next
    INDEX
    Explanations

    durations and time periods

    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
    æĹłèģĬ
    -0.10
    交æĺĵæīĢ
    -0.09
    ä¿Ĺ
    -0.09
    å®ĮæĪIJåIJİ
    -0.09
    aho
    -0.09
    èĬij
    -0.08
    EXIT
    -0.08
    ãģĻãģIJ
    -0.08
    apse
    -0.08
    æ³®
    -0.08
    POSITIVE LOGITS
     sake
    0.10
     purposes
    0.10
    æļĤ
    0.10
     awhile
    0.10
    æķ´æķ´
    0.10
    amina
    0.10
    å¾Īéķ¿æŶéĹ´
    0.09
    å¼Ģå±ķäºĨ
    0.09
    å¾Īéķ¿
    0.09
    ä¸Ģ段æŶéĹ´
    0.09
    Activations Density 0.150%

    No Known Activations