© 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. 21994
    Prev
    Next
    INDEX
    Explanations

    panel lists and legal contexts

    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
    æł·çļĦ
    -0.15
    -0.10
    illery
    -0.09
    peria
    -0.09
    çIJĨä¼ļ
    -0.09
    sis
    -0.09
    ech
    -0.09
    误ä¼ļ
    -0.08
    æµ£
    -0.08
    æ¾¹
    -0.08
    POSITIVE LOGITS
    ists
    0.10
    ares
    0.10
    ter
    0.10
    åŃIJéĩĮ
    0.10
    aky
    0.09
    ing
    0.09
    ize
    0.09
    atic
    0.09
    åĮĸçļĦ
    0.09
    led
    0.09
    Activations Density 0.014%

    No Known Activations