© 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. 56109
    Prev
    Next
    INDEX
    Explanations

    company identifiers followed by "is"

    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
    ãĤ¯ãĥ©ãĥĸ
    -0.09
    æĥ³èµ·æĿ¥
    -0.09
    俱ä¹IJéĥ¨
    -0.08
    身åŃIJ
    -0.08
    urity
    -0.08
    çĬ¶æĢģä¸ĭ
    -0.08
    åĿij
    -0.08
    æĮĩæĮ¥
    -0.08
    desk
    -0.08
    ids
    -0.08
    POSITIVE LOGITS
    ç®Ģ称
    0.13
    åĢĴéĹŃ
    0.13
    åĪĽå§ĭ人
    0.12
    æĪIJç«ĭäºİ
    0.11
    æĹĹä¸ĭ
    0.11
    åĩºåĵģ
    0.11
    æĹĹä¸ĭçļĦ
    0.10
    ä¸Ģç±»
    0.10
    orca
    0.10
    æľīéĻIJåħ¬åı¸
    0.10
    Activations Density 0.273%

    No Known Activations