© 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. 23846
    Prev
    Next
    INDEX
    Explanations

    the world

    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
    #__
    -0.10
    å°¼æĸ¯
    -0.09
    _cu
    -0.09
    å°Ķæĸ¯
    -0.09
    æ±°
    -0.09
    ocl
    -0.09
    æľŁåĨħ
    -0.09
    å¸Ĥå§Ķ常å§Ķ
    -0.09
    manent
    -0.09
    mana
    -0.09
    POSITIVE LOGITS
    人士
    0.13
    讳
    0.10
     tow
    0.10
    éļĪ
    0.09
    rat
    0.08
    èįľ
    0.08
    à´³
    0.08
    Ñĥк
    0.08
    5
    0.08
     humble
    0.08
    Activations Density 0.037%

    No Known Activations