© 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. 31986
    Prev
    Next
    INDEX
    Explanations

    Mango Marshmallow Oneiric Ocelot

    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
    åĴĮ社ä¼ļ
    -0.09
    æı½
    -0.09
    /drivers
    -0.08
    æľ´ç´ł
    -0.08
     Jes
    -0.08
    ä¸Ģä¸ĸ
    -0.07
    åĵģ
    -0.07
    çľ¼çľĭ
    -0.07
    äºİæĺ¯æĪij
    -0.07
    åĪ¶
    -0.07
    POSITIVE LOGITS
    _VO
    0.10
    ERIC
    0.09
    é¢ĦæĬ¥
    0.09
    ieme
    0.09
    çįł
    0.09
    座
    0.09
    åIJIJ
    0.09
    avian
    0.09
    åĽ°
    0.09
    èī²
    0.08
    Activations Density 0.016%

    No Known Activations