© 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. 18795
    Prev
    Next
    INDEX
    Explanations

    if any

    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
    æīĢåľ¨åľ°
    -0.09
    aghetti
    -0.09
    å¸Ĥåľºä¸Ĭ
    -0.08
    笥
    -0.08
    -0.08
    ovel
    -0.08
    æıī
    -0.08
    ä¸įå¿į
    -0.08
    è°Ĵ
    -0.08
    ValueCollection
    -0.08
    POSITIVE LOGITS
    çĶļ
    0.11
    ello
    0.10
    çļĤ
    0.10
    à¸Ńà¸Ńà¸Ļ
    0.09
    æľīç½ijåıĭ
    0.09
    æľīçļĦ
    0.09
    èĨĺ
    0.09
     hiç
    0.09
    essor
    0.09
    ела
    0.09
    Activations Density 0.026%

    No Known Activations