© 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. 33275
    Prev
    Next
    INDEX
    Explanations

    container, app, Development, Labs, console, Scene, Fly

    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
    为人
    -0.10
    rub
    -0.09
    çĽ¸ä¿¡å¤§å®¶
    -0.09
    å¸ĮæľĽå¤§å®¶
    -0.08
     use
    -0.08
    IFA
    -0.08
    æĵ¦
    -0.08
    eri
    -0.08
     fade
    -0.08
    è´µ
    -0.08
    POSITIVE LOGITS
    çªĪ
    0.10
     diet
    0.10
    COPE
    0.10
    ä¼ļéķ¿
    0.10
     Diet
    0.09
    ะ
    0.09
     reins
    0.09
    祢
    0.09
    kish
    0.09
    åĸ»
    0.08
    Activations Density 0.317%

    No Known Activations