© 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. 58681
    Prev
    Next
    INDEX
    Explanations

    extension, adoption, dean, dimensions

    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
    éĴĹ
    -0.10
    æķ´é¡¿
    -0.09
    åĮ»çĸĹåĻ¨æ¢°
    -0.08
    amespace
    -0.08
    æIJ½
    -0.08
    åŃĺ
    -0.08
    æŀķ头
    -0.08
    ç¥ĵ
    -0.08
    åīĬ
    -0.08
    tright
    -0.08
    POSITIVE LOGITS
    Extension
    0.10
    iner
    0.10
    ounty
    0.09
    cala
    0.09
     Extension
    0.09
    æݨ广
    0.09
    extension
    0.09
    éĴī
    0.09
    зв
    0.09
    æĻ®åıĬ
    0.09
    Activations Density 0.063%

    No Known Activations