© 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. 6750
    Prev
    Next
    INDEX
    Explanations

    public places

    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
    岫
    -0.09
    å¡ŀ
    -0.09
    常年
    -0.09
    Tomorrow
    -0.08
    çĴĭ
    -0.08
    å°ĺ
    -0.08
    éĺµèIJ¥
    -0.08
    ieee
    -0.08
    زاد
    -0.08
    inition
    -0.08
    POSITIVE LOGITS
    åĩºè¡Į
    0.15
    èµ°åľ¨
    0.14
    åħ¬åħ±åľºæīĢ
    0.14
    å¤ĸåĩº
    0.13
    æķ£æŃ¥
    0.13
    åĩºåĽ½
    0.12
    éĢĽè¡Ĺ
    0.12
    æĹħè¡Į
    0.11
    éĥĬ
    0.11
    æŃ¥è¡Į
    0.11
    Activations Density 0.174%

    No Known Activations