© 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. 63734
    Prev
    Next
    INDEX
    Explanations

    legal case context

    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
    edList
    -0.10
    heim
    -0.09
     Pand
    -0.09
    çĤ®
    -0.09
    产ä¸ļéĽĨ群
    -0.09
    abled
    -0.09
    liness
    -0.09
    åĻ¨
    -0.08
    å¥ı
    -0.08
    ed
    -0.08
    POSITIVE LOGITS
    侦
    0.11
    亵
    0.09
    æ¶ī
    0.09
     trous
    0.09
    妲
    0.09
    ç¿»
    0.09
    ampo
    0.09
    wagon
    0.08
    åľ¨çݩ家
    0.08
    è¿Ľå±ķ
    0.08
    Activations Density 0.078%

    No Known Activations