© 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. 34612
    Prev
    Next
    INDEX
    Explanations

    no obligation or deposit

    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
    akov
    -0.09
    _GPU
    -0.08
    ç¡®
    -0.08
    天æīį
    -0.08
     FLAGS
    -0.08
    ostream
    -0.08
    å¥Ī
    -0.08
    çĽĹ
    -0.08
     Wars
    -0.08
    亲å±ŀ
    -0.08
    POSITIVE LOGITS
    ëŀĮ
    0.09
    æ§İ
    0.09
    篦
    0.09
    иÑĤелей
    0.09
    åīįçŀ»æĢ§
    0.09
    ä¸Ģå¾ĭ
    0.09
    apos
    0.09
    èĵĸ
    0.09
    ä½ļ
    0.09
    å°Ŀè¯ķ
    0.09
    Activations Density 0.021%

    No Known Activations