© 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. 58569
    Prev
    Next
    INDEX
    Explanations

    leaves

    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
    主ä¹ī
    -0.09
    æ°Ķ象
    -0.09
    irk
    -0.09
    主ä¹īèĢħ
    -0.09
    åıĹ害èĢħ
    -0.09
    -grow
    -0.09
    çļĦçģµéŃĤ
    -0.09
    æĿ¼
    -0.09
    æĶ¾åĩº
    -0.09
     CONTRIBUTORS
    -0.09
    POSITIVE LOGITS
    ves
    0.09
    å¾Īéķ¿
    0.08
    qli
    0.08
    беж
    0.08
    mos
    0.08
    èĴĮ
    0.08
    vestment
    0.08
    ook
    0.08
    ç¿ģ
    0.08
    æ·±å¤Ħ
    0.08
    Activations Density 0.025%

    No Known Activations