© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50935
    Prev
    Next
    INDEX
    Explanations

    able to

    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
    åłĨæĶ¾
    -0.09
    alled
    -0.09
     ICT
    -0.09
    ICT
    -0.09
    è¾IJ
    -0.08
    æĢİä¹Īçľĭ
    -0.08
    angles
    -0.08
     nond
    -0.08
    igers
    -0.08
    åı¬
    -0.08
    POSITIVE LOGITS
    è´¡çĮ®
    0.11
    为广大
    0.10
    亲身
    0.10
    äº²çľ¼
    0.10
    亲èĩª
    0.10
    åıªä¸įè¿ĩæĺ¯
    0.10
     Chr
    0.09
    å¥īçĮ®
    0.09
    _CRE
    0.09
    帮
    0.09
    Activations Density 0.022%

    No Known Activations