© 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. 1798
    Prev
    Next
    INDEX
    Explanations

    time followed by a state or event

    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
    pha
    -0.10
    åѦåłĤ
    -0.09
    lemen
    -0.09
    åĭĥåĭĥ
    -0.09
    Enlarge
    -0.09
    çĸij
    -0.09
    isle
    -0.08
     Elite
    -0.08
    homepage
    -0.08
    æľĶ
    -0.08
    POSITIVE LOGITS
    able
    0.12
    åľ¨ä»Ĭå¹´
    0.09
    ables
    0.09
    åľ¨äº¬
    0.09
    piece
    0.08
    ableObject
    0.08
    éĽī
    0.08
    èĮĮ
    0.08
    æľīæĿ¡ä»¶çļĦ
    0.08
    abouts
    0.08
    Activations Density 0.176%

    No Known Activations