© 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. 6822
    Prev
    Next
    INDEX
    Explanations

    right place, way, or decision

    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
    æIJŀ好
    -0.09
    ç¬ij容
    -0.09
    æĭ¬
    -0.09
    廨
    -0.09
    ULD
    -0.08
    éŀł
    -0.08
     Dawn
    -0.08
     prefer
    -0.08
    çıį
    -0.08
     Fountain
    -0.08
    POSITIVE LOGITS
    群
    0.11
    è¿ĻéĩĮæĺ¯
    0.11
    äºİæѤ
    0.10
    ç½ijéĢļ
    0.10
     Manuals
    0.09
    åħµ
    0.09
    ç»Ī身
    0.09
    alse
    0.09
    mite
    0.09
    asar
    0.09
    Activations Density 0.012%

    No Known Activations