© 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. 53309
    Prev
    Next
    INDEX
    Explanations

    recent history or recent past

    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
    æĹ¢æľī
    -0.11
    NC
    -0.11
    ä¹ĥ
    -0.09
    erved
    -0.09
    nc
    -0.09
    ullen
    -0.09
    kul
    -0.08
    ç®ķ
    -0.08
    æ¼Ĥ
    -0.08
    æĹ¢èĥ½
    -0.08
    POSITIVE LOGITS
    çĽ¸å¯¹è¾ĥ
    0.16
     recent
    0.12
    ä¸įä¹ħ
    0.12
    åĪļåĪļ
    0.11
    æľĢè¿ij
    0.11
     relatively
    0.11
     newest
    0.11
    ä¸įæĺ¯å¾Ī
    0.11
     recently
    0.10
     newer
    0.10
    Activations Density 0.119%

    No Known Activations