© 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. 26374
    Prev
    Next
    INDEX
    Explanations

    fall, fallen, falling

    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
    ually
    -0.11
    æ²½
    -0.10
    åijĺ
    -0.10
    ilter
    -0.10
     kidd
    -0.09
    ette
    -0.09
    елÑı
    -0.09
    èĻº
    -0.09
    antor
    -0.09
    ally
    -0.09
    POSITIVE LOGITS
    acious
    0.11
    èIJ½åĪ°
    0.10
    acies
    0.10
    owed
    0.10
    uate
    0.10
    ows
    0.10
    shipping
    0.10
    -rise
    0.10
    ÑĤоÑĢ
    0.10
    èIJ½
    0.10
    Activations Density 0.030%

    No Known Activations