© 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. 32237
    Prev
    Next
    INDEX
    Explanations

    rank of, rank VII, ranks

    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
    å¿ĥ缮ä¸Ń
    -0.09
    ium
    -0.09
    asters
    -0.08
    èĢģ人家
    -0.08
    éŨæĪ·
    -0.08
    aben
    -0.08
     возможноÑģÑĤи
    -0.08
     rigged
    -0.08
    çīĩåŃIJ
    -0.08
    gest
    -0.08
    POSITIVE LOGITS
    ëį°
    0.10
    nung
    0.10
    ething
    0.10
    owitz
    0.09
    社ä¼ļåĮĸ
    0.09
    ãĥıãĤ¦
    0.09
    ixmap
    0.09
    ings
    0.09
    ademic
    0.09
    otron
    0.09
    Activations Density 0.018%

    No Known Activations