© 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. 60911
    Prev
    Next
    INDEX
    Explanations

    language and literary works

    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
    pipes
    -0.08
    ead
    -0.08
    igator
    -0.08
    anza
    -0.08
    -Men
    -0.08
    ADB
    -0.08
    OrUpdate
    -0.08
    -minus
    -0.08
    aan
    -0.08
     конÑģÑĤÑĢÑĥкÑĨи
    -0.07
    POSITIVE LOGITS
    -speaking
    0.15
    -language
    0.09
    æĽľ
    0.09
    ophone
    0.09
    æĺŁçIJĥ
    0.08
    æĺ§
    0.08
    åľ¨ç¾İåĽ½
    0.08
    çīĪ
    0.08
    æ¹¾
    0.08
    éĿ¢åŃĶ
    0.08
    Activations Density 0.073%

    No Known Activations