© 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. 11531
    Prev
    Next
    INDEX
    Explanations

    fleet of

    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
    atti
    -0.10
    ãĥ³ãĤ°
    -0.10
    ÑĮ
    -0.09
    æĢĢéĩĮ
    -0.09
    åľ°å¸¦
    -0.09
    åħ¶æīĢ
    -0.08
    äºŃ
    -0.08
    èĮ§
    -0.08
    oker
    -0.08
    fas
    -0.08
    POSITIVE LOGITS
    wide
    0.11
    -wide
    0.10
    wright
    0.10
    ä¼į
    0.09
    kinson
    0.09
    ç°ĩ
    0.09
    ÑĤин
    0.09
    èĩ³æĸ¼
    0.09
    èĩ³äºİ
    0.09
    eners
    0.09
    Activations Density 0.006%

    No Known Activations