© 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. 57195
    Prev
    Next
    INDEX
    Explanations

    actions and statements

    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
    èħ¾
    -0.09
    çIJĨ解åĴĮ
    -0.09
    igham
    -0.09
    éĽĨ
    -0.09
    åIJŀ
    -0.08
    ÑĨев
    -0.08
    çĶĦ
    -0.08
    好çľĭ
    -0.08
    继æī¿
    -0.08
    管çIJĨåĴĮ
    -0.08
    POSITIVE LOGITS
    amp
    0.10
    çĿ
    0.10
    æijĶåĢĴ
    0.09
    iola
    0.09
    许
    0.09
    æľīåħ³è§Ħå®ļ
    0.08
    ä»į
    0.08
    æĪIJéķ¿ä¸º
    0.08
    åIJĮæľŁ
    0.08
    éĺĹ
    0.08
    Activations Density 0.089%

    No Known Activations