© 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. 48710
    Prev
    Next
    INDEX
    Explanations

    sprout or out

    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
    é¢ģ
    -0.10
    纵横
    -0.10
    çĶ¨å·¥
    -0.09
    å¾Ģè¿Ķ
    -0.09
    èķī
    -0.09
    ä¹ł
    -0.09
    éļ¾çĤ¹
    -0.09
    纵
    -0.09
    縱
    -0.09
    纯粹
    -0.09
    POSITIVE LOGITS
    å¸Ń
    0.09
    å´´
    0.09
    å¤ļä½Ļ
    0.08
    2
    0.08
    1
    0.08
    ลà¸Ń
    0.08
    ontology
    0.08
    -loader
    0.08
    FromBody
    0.08
    åĿł
    0.08
    Activations Density 0.064%

    No Known Activations