© 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. 50305
    Prev
    Next
    INDEX
    Explanations

    get me to wonder

    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
    ç®ķ
    -0.11
    ibe
    -0.09
    åĩºå¤Ħ
    -0.09
    oki
    -0.09
    çѵ
    -0.08
    ippet
    -0.08
    CMP
    -0.08
    å®īçĦ¶
    -0.08
     Rooney
    -0.08
    æĿ¥èĩªäºİ
    -0.08
    POSITIVE LOGITS
    æĢĿèĢĥ
    0.12
    说çļĦæĺ¯
    0.11
    æ¸į
    0.10
    常说
    0.10
    ä½ı
    0.09
    课å¤ĸ
    0.09
     rid
    0.09
    YS
    0.09
    balls
    0.08
    éĩįçĤ¹åħ³æ³¨
    0.08
    Activations Density 0.021%

    No Known Activations