© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7546
    Prev
    Next
    INDEX
    Explanations

    fax, modem, xerox, sim

    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
    ä»£è¡¨åĽ¢
    -0.10
    缸åºĶ
    -0.10
    å¯Į
    -0.09
    è¹Ń
    -0.09
    æľīæĦı
    -0.09
    ç©¿æĪ´
    -0.09
    缸åºĶçļĦ
    -0.08
    èĪĢ
    -0.08
    éħĮ
    -0.08
    ä¸į顾
    -0.08
    POSITIVE LOGITS
    oo
    0.11
    ä¸Ģ份
    0.11
    åĴĮ个人
    0.09
    å¯Ħ
    0.09
    /email
    0.09
    WithName
    0.09
    ILON
    0.09
    çĻ½è¡£
    0.09
    äºĨä¸Ģ份
    0.09
    ed
    0.08
    Activations Density 0.004%

    No Known Activations