© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36797
    Prev
    Next
    INDEX
    Explanations

    tyres, boots, feet, tires

    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
    æĮ¥
    -0.09
    å·§
    -0.08
    Filed
    -0.08
    è¾¹
    -0.08
    gy
    -0.08
    éĿ¥
    -0.08
     jump
    -0.08
    gnu
    -0.08
     lessons
    -0.07
    èIJ¥
    -0.07
    POSITIVE LOGITS
    éĿ´
    0.13
    èĦļä¸ĭ
    0.13
    è½®èĥİ
    0.12
    å±IJ
    0.12
    ä¸ĢåıĮ
    0.11
    éŀĭ
    0.10
    æľĭ
    0.10
     tyres
    0.10
    èħ³
    0.10
    å±¥
    0.10
    Activations Density 0.122%

    No Known Activations