© 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. 2157
    Prev
    Next
    INDEX
    Explanations

    see, visible, access

    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
    åĩºå¤Ħ
    -0.09
    atron
    -0.09
    è¦ģçŁ¥éģĵ
    -0.08
    åľ¨å®¶
    -0.08
    对åĨ³
    -0.08
    iddy
    -0.08
     Parliament
    -0.08
    åIJİæİĴ
    -0.08
     Burger
    -0.08
     gerekt
    -0.08
    POSITIVE LOGITS
    åĪ«äººçļĦ
    0.10
    mour
    0.09
    å¯Łè§ī
    0.09
    /mit
    0.09
    æıĨ
    0.09
    ä»Ģä¹Īåij¢
    0.09
    æķ¬ä¸ļ
    0.09
    нÑĥл
    0.08
    ä¼ļè§īå¾Ĺ
    0.08
    ä¹Łåıªèĥ½
    0.08
    Activations Density 0.085%

    No Known Activations