© 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. 10871
    Prev
    Next
    INDEX
    Explanations

    movie titles or 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
    æĤĦæĤĦ
    -0.10
    ãĤ³ãĥ¡ãĥ³ãĥĪ
    -0.09
    å·¢
    -0.09
     bÃŃ
    -0.09
    åĨľä¸ļçĶŁäº§
    -0.08
    积èĵĦ
    -0.08
    olina
    -0.08
    .registry
    -0.08
    æĭ¿äºĨ
    -0.08
    æ°ĶåĢĻ
    -0.08
    POSITIVE LOGITS
    oge
    0.10
    çļĪ
    0.09
    é¢ħ
    0.09
    淹没
    0.09
    abel
    0.08
    /board
    0.08
    etch
    0.08
    ajs
    0.08
    æĹ¥æĬ¥ç¤¾
    0.08
     backing
    0.08
    Activations Density 0.005%

    No Known Activations