© 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. 58610
    Prev
    Next
    INDEX
    Explanations

    is considered X

    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
    åı¯èĥ½åĩºçİ°
    -0.09
    å®īæĬļ
    -0.08
    骤
    -0.08
    åºļ
    -0.08
    bus
    -0.08
    æĦĶ
    -0.08
     cum
    -0.08
    è¡·
    -0.07
    æijĦ
    -0.07
    _PY
    -0.07
    POSITIVE LOGITS
    èĮ¬
    0.10
    æ±IJ
    0.09
    éĿŀ常好çļĦ
    0.09
    档次
    0.09
    åº
    0.09
    ations
    0.09
    arten
    0.09
    çķĮçļĦ
    0.09
    è¿Ħ
    0.08
    åħ¥åľº
    0.08
    Activations Density 0.059%

    No Known Activations