© 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. 49443
    Prev
    Next
    INDEX
    Explanations

    enabling or allowing

    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
    inate
    -0.08
    ÑĢаÑģ
    -0.08
     Ban
    -0.08
    arel
    -0.08
    æĿĤ
    -0.08
    éĨĴäºĨ
    -0.08
    عÙĬ
    -0.08
    Ĥ¹
    -0.08
    éĤ¬
    -0.08
    ä¸Ģä¸ĭ
    -0.08
    POSITIVE LOGITS
    å¾Ĺ以
    0.15
    çľĭåĩº
    0.12
    顺åĪ©
    0.12
    æijĨèĦ±
    0.12
    åħĭæľį
    0.11
    æĽ´å¥½åľ°
    0.10
    åºķæ°Ķ
    0.10
    åĢŁæѤ
    0.10
     возможноÑģÑĤÑĮ
    0.10
     возможноÑģÑĤи
    0.10
    Activations Density 0.094%

    No Known Activations