© 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. 17806
    Prev
    Next
    INDEX
    Explanations

    separate, separately, distinct

    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
    amer
    -0.09
    inton
    -0.09
     Gib
    -0.09
    å¼Ĭ
    -0.09
    -With
    -0.08
    omi
    -0.08
     Bri
    -0.08
    驾é©Ń
    -0.08
    ä¼ģä¸ļåĴĮ
    -0.08
    ç¿ķ
    -0.08
    POSITIVE LOGITS
    åįķçĭ¬
    0.31
     separate
    0.25
    ä¸ĵéŨ
    0.23
    åı¦è¡Į
    0.23
     riêng
    0.22
    åĪĨå¼Ģ
    0.21
     separately
    0.20
     Separate
    0.19
     seperate
    0.18
    çĭ¬ç«ĭ
    0.17
    Activations Density 0.273%

    No Known Activations