© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 1388
    Prev
    Next
    INDEX
    Explanations

    extremism, terror, or harmful content

    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
    åĴĮæĬĢæľ¯
    -0.10
    æŃĩ
    -0.09
     RDD
    -0.09
    æĢķ
    -0.09
    æħij
    -0.08
    éĶ»çĤ¼
    -0.08
     OPTIONAL
    -0.08
    Nonce
    -0.08
    èĢį
    -0.08
    ä¸ĢåĪĢ
    -0.08
    POSITIVE LOGITS
    é«ĺéĢŁ
    0.10
    antium
    0.09
    å¢Ļä¸Ĭ
    0.09
    zos
    0.09
    离èģĮ
    0.09
    ÐľÐIJ
    0.09
    论
    0.09
    æ²¾
    0.09
    é«ĺéĢŁåħ¬è·¯
    0.08
    _METADATA
    0.08
    Activations Density 0.290%

    No Known Activations