© 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. 61223
    Prev
    Next
    INDEX
    Explanations

    night vision owl shift

    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
    çŀ¬
    -0.10
     Graves
    -0.09
    åıĮéĩį
    -0.09
    è¯ķæİ¢
    -0.09
    åĪ¹éĤ£
    -0.09
     Grain
    -0.09
    ItemAt
    -0.09
    å«¡
    -0.09
    符åı·
    -0.08
    овÑĭй
    -0.08
    POSITIVE LOGITS
    OWL
    0.09
    lav
    0.09
    fully
    0.09
    æĦı大
    0.08
    shade
    0.08
    çĶŁæ´»çļĦ
    0.08
    ä¸ĢæĹı
    0.08
    mess
    0.08
    оз
    0.08
    åĽłä¸ºæĪij
    0.08
    Activations Density 0.019%

    No Known Activations