© 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. 47669
    Prev
    Next
    INDEX
    Explanations

    prevention, management, treatment

    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
    æŃ£å¸¸ä½¿çĶ¨
    -0.10
    åĩºç§Ł
    -0.09
    ikt
    -0.09
    fabric
    -0.09
    /man
    -0.09
    гал
    -0.09
     Lois
    -0.09
    å¥
    -0.08
     Babylon
    -0.08
    ems
    -0.08
    POSITIVE LOGITS
     prevention
    0.12
    综åIJĪæ²»çIJĨ
    0.11
    _handling
    0.10
    çĹĩ
    0.10
     Prevention
    0.10
    æĶ»åĿļæĪĺ
    0.09
    严éĩįçļĦ
    0.09
    é¢Ħéĺ²
    0.09
    æģ¶
    0.09
    -Free
    0.09
    Activations Density 0.522%

    No Known Activations