© 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. 36155
    Prev
    Next
    INDEX
    Explanations

    central park

    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
    çĩİ
    -0.09
    orp
    -0.09
    è¾°
    -0.08
    è¿Ļ个人
    -0.08
    çķĻåľ¨
    -0.08
    æŀģ
    -0.08
    é»İ
    -0.08
     Jerusalem
    -0.08
    é»İæĺİ
    -0.08
    èĪ±
    -0.08
    POSITIVE LOGITS
    éĩĮéĿ¢çļĦ
    0.11
    éĩĮéĿ¢æľī
    0.10
    зал
    0.09
    morgan
    0.09
    æĢĢæĬ±
    0.09
    mods
    0.09
     dane
    0.09
    ancell
    0.09
    виÑĤ
    0.09
     ``(
    0.09
    Activations Density 0.012%

    No Known Activations