© 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. 61502
    Prev
    Next
    INDEX
    Explanations

    locations near junctions

    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
    èį£å¹¸
    -0.10
    æĽĽ
    -0.10
    ripp
    -0.09
    åįĵ
    -0.09
     Hanging
    -0.09
    ми
    -0.09
    ONO
    -0.09
    æĮ¯åħ´
    -0.09
    æŁı
    -0.08
     lit
    -0.08
    POSITIVE LOGITS
    åĺ´è§Ĵ
    0.09
    æݥ触åĪ°
    0.09
     where
    0.09
    ä¸ĢåIJ¬
    0.09
    ellow
    0.08
    where
    0.08
     jun
    0.08
    utzer
    0.08
    羣æŃ£åģļåĪ°
    0.08
    anz
    0.08
    Activations Density 0.098%

    No Known Activations