© 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. 49484
    Prev
    Next
    INDEX
    Explanations

    from the

    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
    éĴĪ
    -0.09
     fac
    -0.09
    èĩªæķij
    -0.08
    æ²»å®ī
    -0.08
    ç¹ģ
    -0.08
    å¾Ī好çļĦ
    -0.08
    æł¡åĮº
    -0.08
     forts
    -0.08
    æĭĻ
    -0.08
    æĺ¥èĬĤ
    -0.08
    POSITIVE LOGITS
    edes
    0.12
    rides
    0.10
    éro
    0.09
    ryn
    0.09
    tings
    0.09
    åħļæĢ»
    0.09
    xEB
    0.09
    åIJİæŀľ
    0.09
    .TAG
    0.09
    aggi
    0.09
    Activations Density 0.028%

    No Known Activations