© 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. 27410
    Prev
    Next
    INDEX
    Explanations

    read, click, delete, set

    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
    åĬĪ
    -0.10
    nee
    -0.10
    _relations
    -0.09
    饴
    -0.09
    æŁ±
    -0.09
     MERCHANTABILITY
    -0.09
    è¾¹
    -0.09
    è°ĥåīĤ
    -0.09
    诤
    -0.09
    _SETUP
    -0.09
    POSITIVE LOGITS
    红æĹĹ
    0.11
    åľ¨ç½ijä¸Ĭ
    0.09
    èĮĦ
    0.08
    å²ģæŶ
    0.08
    æ¢Ŀ
    0.08
     easily
    0.08
    æįĤ
    0.08
    èĮ¹
    0.08
    dere
    0.08
    ä¸Ģè§Ĵ
    0.07
    Activations Density 0.017%

    No Known Activations