© 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. 19297
    Prev
    Next
    INDEX
    Explanations

    administrative, restaurants, cure, cyst

    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
    -0.10
    asty
    -0.10
    好象
    -0.09
    好çľĭçļĦ
    -0.09
    ä½Ĩä¸įéĻIJ
    -0.08
    æĬĢæľ¯äººåijĺ
    -0.08
    etus
    -0.08
    NECT
    -0.08
    çĥ«
    -0.08
    çĸĿ
    -0.08
    POSITIVE LOGITS
    æľīæŶåĢĻ
    0.09
    ivist
    0.09
    cheid
    0.08
    iaux
    0.08
    iev
    0.08
    嬿
    0.08
    IVEN
    0.07
     passions
    0.07
    æľī幸
    0.07
    .sig
    0.07
    Activations Density 1.025%

    No Known Activations