© 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. 58484
    Prev
    Next
    INDEX
    Explanations

    beginning of each

    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
    обоÑĢ
    -0.09
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    -0.09
    æĽ·
    -0.09
    çķĻåŃĺ
    -0.08
    ury
    -0.08
    佬
    -0.08
    bus
    -0.08
    åĩłæŃ¥
    -0.08
     Ned
    -0.08
    åIJĦ个çݯèĬĤ
    -0.07
    POSITIVE LOGITS
    iance
    0.10
    cente
    0.09
     respective
    0.09
    zego
    0.09
    cala
    0.09
    -equiv
    0.09
    deen
    0.09
    dong
    0.08
    æľīæľŁ
    0.08
    ãģį
    0.08
    Activations Density 0.064%

    No Known Activations