© 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. 59415
    Prev
    Next
    INDEX
    Explanations

    Israel, Gaza, protest, Egypt, Middle East

    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
    Negative Logits
    ÑĢиÑģÑĤ
    -0.09
    _EOL
    -0.09
    Configurer
    -0.09
    èĩ£
    -0.09
    /Sub
    -0.09
    itag
    -0.09
    éĺ²çĽĹ
    -0.08
    MSN
    -0.08
    _mr
    -0.08
    åªĴ
    -0.08
    POSITIVE LOGITS
    ä¸Ģä½ĵåĮĸ
    0.10
    æ¼Ĥæµģ
    0.09
    æłħ
    0.09
    æĶ¯éħį
    0.09
    ãĤ·ãĥ¼ãĤºãĥ³
    0.08
    ious
    0.08
    7
    0.08
    åı¯è¾¾
    0.08
    好äºĨ
    0.08
    æIJĶ
    0.08
    Activations Density 0.104%

    No Known Activations