© 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. 4378
    Prev
    Next
    INDEX
    Explanations

    addition to

    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
    满满çļĦ
    -0.11
    å¾Ĺä½ı
    -0.10
    sdale
    -0.10
    è§ģè¿ĩ
    -0.10
    æ´¼
    -0.10
    èĥĮä¸Ĭ
    -0.10
    顾
    -0.09
    å°»
    -0.09
    ä¸Ĭå¸Ŀ
    -0.09
    .fm
    -0.09
    POSITIVE LOGITS
    itions
    0.11
    OrUpdate
    0.10
    ition
    0.09
    ITION
    0.09
    åŁİåĮº
    0.09
    ality
    0.09
    arity
    0.09
    ional
    0.09
    ary
    0.09
    itial
    0.09
    Activations Density 0.010%

    No Known Activations