© 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. 30604
    Prev
    Next
    INDEX
    Explanations

    marine gastropod mollusks

    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
    å°ıé¾Ļ
    -0.10
    ä¸IJ
    -0.09
    åIJĮæ¯Ķ
    -0.09
    åįĩ温
    -0.09
    _DBG
    -0.08
    åı»
    -0.08
    å·¢
    -0.08
    éĴī
    -0.08
    æıŃ示
    -0.08
    .micro
    -0.08
    POSITIVE LOGITS
    subscribe
    0.10
    Subscribe
    0.10
     disap
    0.09
    .getvalue
    0.09
    åį·
    0.09
    orp
    0.09
    ç¼Ŀ
    0.09
    åIJį人
    0.08
    èĴ½
    0.08
    urent
    0.08
    Activations Density 0.185%

    No Known Activations