© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37515
    Prev
    Next
    INDEX
    Explanations

    (c) Enalean, 2019-Present. All Rights Reserved

    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
    è··
    -0.10
    ä¸ĵä¸ļä»İäºĭ
    -0.09
    heads
    -0.09
    iced
    -0.09
    MOTE
    -0.08
    è¿ĻåIJį
    -0.08
    alin
    -0.08
    ãģĴ
    -0.08
     thirsty
    -0.08
    ç§įç±»
    -0.08
    POSITIVE LOGITS
    ä¸ĢçĤ¹
    0.10
    _prediction
    0.10
    arium
    0.09
    åıªè¦ģæĺ¯
    0.09
    dio
    0.09
     Gast
    0.08
    çĵł
    0.08
    è´®
    0.08
    ç´¯
    0.08
    侧
    0.08
    Activations Density 0.205%

    No Known Activations