© 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. 54598
    Prev
    Next
    INDEX
    Explanations

    wearing or looking like

    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
     Ùħض
    -0.09
    å±ŀäºİèĩªå·±
    -0.09
    -Oct
    -0.09
     yapılır
    -0.09
    ownt
    -0.09
    ILD
    -0.09
    家ä¸Ń
    -0.09
    esz
    -0.08
    éĹ®è´£
    -0.08
    IDD
    -0.08
    POSITIVE LOGITS
    ä¼¼ä¹İ
    0.12
    ä¼¼ä¹İæĺ¯
    0.11
    好åĥı
    0.11
    éļĶçĿĢ
    0.10
    æĢİä¹Īçľĭ
    0.10
    好åĥıæĺ¯
    0.10
     seems
    0.10
    大约
    0.09
    ç»Ļ人ä¸Ģç§į
    0.09
    ç©¿çĿĢ
    0.09
    Activations Density 0.069%

    No Known Activations