© 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. 3528
    Prev
    Next
    INDEX
    Explanations

    inland storm movement

    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
    boa
    -0.10
    åľ®
    -0.10
    Sink
    -0.10
     ìĭľ
    -0.09
    åħ´èµ·
    -0.09
    沸èħ¾
    -0.09
    åĨľå®¶ä¹IJ
    -0.09
    åľ°éĿ¢
    -0.09
    .Binding
    -0.08
    pest
    -0.08
    POSITIVE LOGITS
    çĴ§
    0.12
    è¿ĩæĿ¥
    0.09
    ç¢Į
    0.09
    æĮŁ
    0.08
    为广大
    0.08
    æĬij
    0.08
    æĬī
    0.08
    çĪ¬
    0.08
    kees
    0.08
     established
    0.08
    Activations Density 0.033%

    No Known Activations