© 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. 5706
    Prev
    Next
    INDEX
    Explanations

    suitable substitute legal

    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
     özel
    -0.10
    å¥
    -0.10
    .dest
    -0.09
     Hood
    -0.09
    éŃĶ
    -0.08
    .nodeType
    -0.08
    æļĿ
    -0.08
    åĽ¿
    -0.08
    haps
    -0.08
     SOM
    -0.08
    POSITIVE LOGITS
    æ²£
    0.10
    åºIJ
    0.10
    ç°Į
    0.09
    èģļ
    0.09
    ä¸įåı¯
    0.09
    åľ¨èģĮ
    0.09
    ä»£è¡¨åĽ¢
    0.08
    abal
    0.08
     perms
    0.08
    è´¨åľ°
    0.08
    Activations Density 0.004%

    No Known Activations