© 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. 23082
    Prev
    Next
    INDEX
    Explanations

    priming, two studies, sourcing, Mage, After completing, subjects, field

    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
     @@
    -0.10
    éģ¿
    -0.10
    主è§Ĥ
    -0.09
    å®ŀçī©
    -0.09
    é¢Ī
    -0.09
    继
    -0.09
    @student
    -0.09
    åľ¨è¿ĩæ¸¡æľŁ
    -0.09
    çĨĻ
    -0.09
    ä»»æĢ§
    -0.08
    POSITIVE LOGITS
    èĢĹ
    0.10
    æįĭ
    0.10
    åķĨåľº
    0.09
    é£ĺ
    0.09
    åķĨåŁİ
    0.09
    _armor
    0.09
    èģĶç½ij
    0.08
    温æļĸ
    0.08
    /cs
    0.08
    工夫
    0.08
    Activations Density 0.202%

    No Known Activations