© 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. 27718
    Prev
    Next
    INDEX
    Explanations

    separating elements

    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
    iendo
    -0.09
    éĴĿ
    -0.08
    inated
    -0.08
    ä¸įå¦Ĥ
    -0.08
    è¿Ļæĺ¯åĽłä¸º
    -0.08
    ä¸įåıĬ
    -0.08
    è°ħ
    -0.08
    æ±ľ
    -0.08
    UTOR
    -0.08
    este
    -0.08
    POSITIVE LOGITS
    ype
    0.09
    (SYS
    0.09
    otron
    0.08
    è¦ģéĹ»
    0.08
     nap
    0.08
    èĿĪ
    0.08
    referrer
    0.08
    OrDefault
    0.08
    åīįåįģ
    0.08
    æ¯Ķäºļ
    0.07
    Activations Density 0.189%

    No Known Activations