© 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. 31658
    Prev
    Next
    INDEX
    Explanations

    cost or price

    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
    åħ³éĶ®æĺ¯
    -0.09
    /swagger
    -0.08
    endance
    -0.08
    ÑģеÑĤ
    -0.08
    csr
    -0.08
    -refresh
    -0.08
    éľİ
    -0.08
    缴å±ŀ
    -0.08
    çļĦäºĭ
    -0.07
    çļĦæīĢæľī
    -0.07
    POSITIVE LOGITS
    æĸ¹å¼ıè¿Ľè¡Į
    0.12
    /by
    0.11
    æİīäºĨ
    0.10
    æĮĩ导ä¸ĭ
    0.10
    /at
    0.10
    æĿ¡ä»¶ä¸ĭ
    0.09
    çĬ¶æĢģä¸ĭ
    0.09
    èħ®
    0.09
    èĢĮä¸įæĺ¯
    0.09
     manner
    0.09
    Activations Density 0.355%

    No Known Activations