© 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. 27537
    Prev
    Next
    INDEX
    Explanations

    medium of or medium.com

    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
    ãĤĪãģĨãģª
    -0.10
    fully
    -0.09
    ÑĦикÑģ
    -0.08
    åħ±åIJĮä½ĵ
    -0.08
     конкÑĢеÑĤ
    -0.08
    NOWLED
    -0.08
    ãģĦãģĨ
    -0.08
    ứng
    -0.08
    ammer
    -0.08
    procs
    -0.08
    POSITIVE LOGITS
    éĸ£
    0.10
    ãģĹãģ¾ãģĨ
    0.10
    èĮ§
    0.10
    sk
    0.09
    sWith
    0.09
    çĹ£
    0.09
    éĺģ
    0.09
    ели
    0.08
    akt
    0.08
    åīĥ
    0.08
    Activations Density 0.012%

    No Known Activations