© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53219
    Prev
    Next
    INDEX
    Explanations

    recently followed by past action

    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
     eventual
    -0.13
    æĹ¥åIJİ
    -0.10
    oute
    -0.10
    ä¸Ģå®ļçļĦ
    -0.09
     eventually
    -0.09
    gebra
    -0.09
    å¦ĤæľŁ
    -0.09
     Nina
    -0.09
    å½ĵåĪĿ
    -0.09
    ready
    -0.09
    POSITIVE LOGITS
    çķ¿
    0.11
    umb
    0.10
    æľī人
    0.10
    usz
    0.09
    宪
    0.09
    ãģ¶ãĤĬ
    0.09
    WARDS
    0.09
    ue
    0.09
    ÑĦоÑĢ
    0.09
    羿
    0.09
    Activations Density 0.028%

    No Known Activations