© 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. 30674
    Prev
    Next
    INDEX
    Explanations

    wisdom and advice

    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
    鬲
    -0.10
    éĻĮçĶŁ
    -0.09
    绫
    -0.09
    arrison
    -0.09
    fel
    -0.09
    空çĻ½
    -0.09
    å¸Ńåį·
    -0.09
    strand
    -0.09
    åį·
    -0.08
     INTERVAL
    -0.08
    POSITIVE LOGITS
     wisdom
    0.24
    æĻºæħ§
    0.21
     Wisdom
    0.19
    wis
    0.17
     advice
    0.17
     wise
    0.17
    æķĻè®Ń
    0.16
     Advice
    0.16
    wise
    0.14
     Wise
    0.14
    Activations Density 0.081%

    No Known Activations