© 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. 6907
    Prev
    Next
    INDEX
    Explanations

    delay time

    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
    elsen
    -0.10
    ãģĹãģ¾ãģĦ
    -0.10
    ä¹Łä¸įæķ¢
    -0.10
    ä¿ij
    -0.10
    ç´¯äºĨ
    -0.09
    麻å°Ĩ
    -0.09
    æł·çļĦ
    -0.09
    åĬĽäºī
    -0.09
    åī¯å±Ģéķ¿
    -0.09
    å¦Ĥä½ķçľĭå¾ħ
    -0.08
    POSITIVE LOGITS
    ataire
    0.11
    ìĤ¬íķŃ
    0.11
    ataires
    0.10
     kiá»ĩn
    0.10
    overs
    0.09
    inous
    0.09
    ormsg
    0.09
    æѤåĪ»
    0.09
    imiters
    0.09
    voor
    0.09
    Activations Density 0.015%

    No Known Activations