© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12156
    Prev
    Next
    INDEX
    Explanations

    intent or intention

    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
    arella
    -0.10
    ä¸įçķĻ
    -0.09
    æIJŃæ¡£
    -0.08
    uchen
    -0.08
    lore
    -0.08
    æİĸ
    -0.08
     tiger
    -0.08
    é¦ĸä½į
    -0.08
    ä½łçľĭ
    -0.08
    rels
    -0.08
    POSITIVE LOGITS
     intent
    0.20
    æĦıåĽ¾
    0.19
     intention
    0.18
    intent
    0.17
     Intent
    0.17
     intentions
    0.17
    (intent
    0.17
     intents
    0.15
    (Intent
    0.15
    .intent
    0.14
    Activations Density 0.046%

    No Known Activations