© 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. 39580
    Prev
    Next
    INDEX
    Explanations

    speaker seems sure

    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
    æģ°æģ°
    -0.10
    å¾Īåı¯èĥ½
    -0.09
    ä¸įå¾Ĺä¸į
    -0.09
    ãģĭãĤĤ
    -0.09
    çѱ
    -0.08
     Ritch
    -0.08
     Morse
    -0.08
     Morrow
    -0.08
    루
    -0.08
    ighb
    -0.08
    POSITIVE LOGITS
    ãģ®ãģĵãģ¨
    0.09
    åĬŀæ³ķ
    0.09
    主æĦı
    0.08
    ecal
    0.08
    okia
    0.08
     somewhere
    0.08
    æįı
    0.08
    ctl
    0.08
    èĥľä»»
    0.08
    è¤Ĭ
    0.08
    Activations Density 0.031%

    No Known Activations