© 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. 49804
    Prev
    Next
    INDEX
    Explanations

    copyright notice

    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
    vice
    -0.08
    éŃĩ
    -0.08
    åIJijå¾Ģ
    -0.08
    åºĶæĢ¥é¢Ħæ¡Ī
    -0.08
    entine
    -0.08
    代表æĢ§
    -0.08
     MOR
    -0.08
    UINT
    -0.08
    /videos
    -0.08
    ä½Ĩæĺ¯ä»ĸ
    -0.08
    POSITIVE LOGITS
    æľĢåħĪè¿ĽçļĦ
    0.09
    verse
    0.09
    é²®
    0.09
    UDGE
    0.09
    çķĮ
    0.09
    éģĤ
    0.09
    itech
    0.09
    è¹ī
    0.09
    opes
    0.08
    èĢį
    0.08
    Activations Density 0.040%

    No Known Activations