© 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. 33863
    Prev
    Next
    INDEX
    Explanations

    legal and news reporting phrases

    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
    anon
    -0.10
    æľį
    -0.10
    åIJĮèĥŀ
    -0.09
    ooke
    -0.09
    çīĪæĿĥæīĢæľī
    -0.09
    avor
    -0.09
    æİīäºĨ
    -0.08
    èį¯å¸Ī
    -0.08
     Rudd
    -0.08
    粤
    -0.08
    POSITIVE LOGITS
    ä½ĵèĤ²
    0.10
    åĪĨæĪIJ
    0.09
    æĭĽçĶŁ
    0.09
    é¼ĭ
    0.09
    UIL
    0.09
    æĤ²åī§
    0.09
    /fa
    0.09
    æľ½
    0.09
    æ§Į
    0.09
    UIS
    0.08
    Activations Density 0.013%

    No Known Activations