© 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. 63264
    Prev
    Next
    INDEX
    Explanations

    Gal\nman\nstone

    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
    åĪ©å¥½
    -0.09
    ä»Ģ
    -0.09
    reste
    -0.09
    ç¹ģ
    -0.09
    emie
    -0.09
    iat
    -0.08
    ä¼į
    -0.08
    åħ¬çĦ¶
    -0.08
    ensis
    -0.08
    dden
    -0.08
    POSITIVE LOGITS
    åķ¸
    0.11
    èķĻ
    0.09
    çĿĢ
    0.09
    antor
    0.09
    çĿĢä»ĸ
    0.09
    æ¼ĵ
    0.09
    è¿ĻåĿĹ
    0.09
     hè
    0.09
    .Modified
    0.09
    çİ°è¡Į
    0.08
    Activations Density 0.001%

    No Known Activations