© 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. 55766
    Prev
    Next
    INDEX
    Explanations

    varieties of colors, finishes, and sizes

    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
    4
    -0.09
    çĭĤ
    -0.09
    0
    -0.08
    ä¸Ńå¿ĥåŁİåĮº
    -0.08
    OWN
    -0.08
    é²®
    -0.08
    ä¸įè´Ł
    -0.08
    7
    -0.08
    ayer
    -0.08
    -devel
    -0.08
    POSITIVE LOGITS
    amel
    0.10
    çİ°éĩij
    0.09
    amac
    0.09
     varieties
    0.09
    éĤ´
    0.09
    æ´ĭ
    0.09
    æĹ»
    0.09
     variations
    0.09
    åıĺå¼Ĥ
    0.08
    è¤ļ
    0.08
    Activations Density 0.041%

    No Known Activations