© 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. 23965
    Prev
    Next
    INDEX
    Explanations

    availability

    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
    ãĤĴãģ¤ãģij
    -0.09
    å®Īä½ı
    -0.09
    æıī
    -0.09
     BP
    -0.08
    循
    -0.08
    è¿Ļ对
    -0.08
    éĵ¶
    -0.08
    agus
    -0.08
    é¢ł
    -0.08
    çĽ²çĽ®
    -0.08
    POSITIVE LOGITS
     vacancies
    0.14
    åIJįé¢Ŀ
    0.13
     availability
    0.13
     available
    0.12
    èħ¾
    0.12
     Availability
    0.11
    éĹ²
    0.11
     Available
    0.11
     vacancy
    0.11
    騰
    0.10
    Activations Density 0.084%

    No Known Activations