© 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. 37856
    Prev
    Next
    INDEX
    Explanations

    with or without

    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
    adier
    -0.10
    agle
    -0.10
    awi
    -0.09
    åĬłåĪĨ
    -0.09
    夷
    -0.09
    ITT
    -0.09
    åľ¨çº¿
    -0.09
    åĪĪ
    -0.08
    éľĵ
    -0.08
    imate
    -0.08
    POSITIVE LOGITS
    åºķæ°Ķ
    0.09
    æĺ¯æĪijåĽ½
    0.09
    ä¸įåĪ°
    0.08
    æĪIJ为ä¸ŃåĽ½
    0.08
    è¿ĺä¸įå¦Ĥ
    0.08
    èĥ½è¾¾åĪ°
    0.08
    éļIJæĤ£
    0.08
    غÙħ
    0.08
    lessness
    0.08
     اÙĦÙī
    0.08
    Activations Density 0.122%

    No Known Activations