© 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. 10077
    Prev
    Next
    INDEX
    Explanations

    Objective-C runtime functions

    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
    /rfc
    -0.11
    çĻĸ
    -0.10
    rove
    -0.09
    éĢ»è¾ij
    -0.09
    积æŀģåıĤä¸İ
    -0.09
    erdem
    -0.09
    /front
    -0.09
    移
    -0.09
    åĪĴ
    -0.09
    æķŀ
    -0.09
    POSITIVE LOGITS
    æīĭèĦļ
    0.09
    æĪ´ä¸Ĭ
    0.09
    anan
    0.08
     ÑģпеÑĨ
    0.08
    ç»ĩ
    0.08
    å±ĢéĻIJäºİ
    0.08
     anom
    0.08
    æķĪæŀľ
    0.08
    åĵªåĦ¿
    0.08
    è·Ľ
    0.08
    Activations Density 0.565%

    No Known Activations