© 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. 18260
    Prev
    Next
    INDEX
    Explanations

    villanova.edu

    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
    éĻ°
    -0.10
    ä¸Ģ家
    -0.09
    éĺ´
    -0.08
    è¦ģæĬĬ
    -0.08
    妣
    -0.08
    åĴ¿
    -0.08
    åĽ½ç«ĭ
    -0.08
    ร
    -0.08
    idi
    -0.08
    åĺĽ
    -0.08
    POSITIVE LOGITS
    éĢĶ
    0.09
    rost
    0.09
    á»įng
    0.09
    ðŁĴĸ
    0.08
    æĴ©
    0.08
    èij£äºĭ
    0.08
     Bris
    0.08
    ÑĢÑİ
    0.08
    _owned
    0.08
     Stoke
    0.08
    Activations Density 0.002%

    No Known Activations