© 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. 4483
    Prev
    Next
    INDEX
    Explanations

    refer to:

    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
    ober
    -0.09
    åıijæİĺ
    -0.09
    ources
    -0.09
     näm
    -0.08
    æĬ½
    -0.08
    nod
    -0.08
    ä¼ļä¸Ĭ
    -0.08
     Bauer
    -0.07
    æľĹ
    -0.07
    èľī
    -0.07
    POSITIVE LOGITS
    座ä½į
    0.10
    æī¼
    0.09
    æĹłç¼ĺ
    0.09
    æ±īè¯Ń
    0.09
    è¿Ļä¸ªåľ°æĸ¹
    0.09
    æŁIJä¸Ģ
    0.09
    æĩĤå¾Ĺ
    0.08
    (thing
    0.08
    _reply
    0.08
    æ¼ı
    0.08
    Activations Density 0.206%

    No Known Activations