© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51139
    Prev
    Next
    INDEX
    Explanations

    day after

    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
    æĬ±
    -0.09
    aison
    -0.09
    åĤį
    -0.09
    adder
    -0.08
    iko
    -0.08
    çīĩ
    -0.08
    aub
    -0.08
    omat
    -0.08
    åĨ¬åŃ£
    -0.08
    oster
    -0.08
    POSITIVE LOGITS
    åĩĮæĻ¨
    0.10
    为广大
    0.10
    ä¸Ģå¤ľ
    0.09
    åºł
    0.09
    overn
    0.09
    æ»Ķ
    0.09
    åĨĴåĩº
    0.09
    ç»ļ丽
    0.09
    ä¸Ģ大æĹ©
    0.09
    å¸ĥç½®
    0.09
    Activations Density 0.024%

    No Known Activations