© 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. 63804
    Prev
    Next
    INDEX
    Explanations

    English language and related contexts

    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
    aris
    -0.09
    ç»ĪçĶŁ
    -0.09
    人éĻħåħ³ç³»
    -0.09
    åİ¥
    -0.08
    åīįæīĢ
    -0.08
    人工
    -0.08
    adic
    -0.08
    SEA
    -0.08
    usi
    -0.08
    åŃIJéĩĮ
    -0.08
    POSITIVE LOGITS
    -speaking
    0.14
    -language
    0.12
    berger
    0.09
    combe
    0.09
    ÑĤеÑĢ
    0.09
    boro
    0.09
    åĨįéĢł
    0.09
     ÙģعÙĦ
    0.09
     Kills
    0.09
    ower
    0.09
    Activations Density 0.043%

    No Known Activations