© 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. 5242
    Prev
    Next
    INDEX
    Explanations

    price changes

    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
    çļĦ巨大
    -0.10
    é¦Ī
    -0.10
    ATAL
    -0.09
    éĹªèĢĢ
    -0.09
    æĭĪ
    -0.09
    æıIJæĹ©
    -0.09
    croll
    -0.09
    çł£
    -0.09
    åĮĻ
    -0.09
    -turn
    -0.09
    POSITIVE LOGITS
    å¤ļå°ij
    0.12
    enet
    0.10
    èĭ¥å¹²
    0.10
    ä¸Ģä¸ĭ
    0.09
    ä¸Ģå®ļçļĦ
    0.09
    äºĽè®¸
    0.09
    2
    0.08
    ä¸ĢæŃ¥
    0.08
    3
    0.08
    çĻ¾åĪĨä¹ĭ
    0.08
    Activations Density 0.053%

    No Known Activations