© 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. 5889
    Prev
    Next
    INDEX
    Explanations

    -shire place names

    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
    rade
    -0.10
    家å±ŀ
    -0.10
    è¿Ļ个æĹ¶ä»£
    -0.09
    æĦıä¹īä¸ĬçļĦ
    -0.09
    urai
    -0.09
    åħ¨åĽ½åIJĦåľ°
    -0.09
    è´µå·ŀ
    -0.09
    arily
    -0.09
    ä¹ĭå¤Ħ
    -0.08
    åĮĹ京åĨ¬å¥¥
    -0.08
    POSITIVE LOGITS
    ousel
    0.11
    æĺİçıł
    0.10
    æµĴ
    0.09
    wide
    0.09
    åħľ
    0.09
    otte
    0.09
    -based
    0.09
    ÑĦан
    0.09
    åĪĨåħ¬åı¸
    0.09
     اÙĦاÙĨ
    0.09
    Activations Density 0.011%

    No Known Activations