© 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. 34542
    Prev
    Next
    INDEX
    Explanations

    Sphinx, riddles, cancer, Leverant

    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
    yı
    -0.10
    MENT
    -0.09
    æĢ»ä¹ĭ
    -0.09
    åĪ°äºĨ
    -0.09
    ion
    -0.09
    ä¸įçķĻ
    -0.09
    amarin
    -0.08
     PACK
    -0.08
    aches
    -0.08
    æ¤ħ
    -0.08
    POSITIVE LOGITS
    owing
    0.10
    ç¬ijè¯Ŀ
    0.09
    oke
    0.09
    æ¹ĸåĮº
    0.09
    naire
    0.09
    atical
    0.09
    éļĻ
    0.08
    ry
    0.08
    èĻİ
    0.08
    ario
    0.08
    Activations Density 0.011%

    No Known Activations