© 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. 50318
    Prev
    Next
    INDEX
    Explanations

    drive business innovation

    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
    lk
    -0.10
    ibo
    -0.10
    çļĦåİĨåı²
    -0.09
    æĥ
    -0.09
    acer
    -0.09
    elian
    -0.09
     ÑģкоÑĢо
    -0.09
    çļĦä¸ľè¥¿
    -0.08
    åĿIJ
    -0.08
    è¯ķ
    -0.08
    POSITIVE LOGITS
    浸
    0.09
    èĢĮæĪIJ
    0.09
    çIJĨ解åĴĮ
    0.08
     innovation
    0.08
    0.08
    åħ¶éĹ´
    0.08
    æŀľçĦ¶
    0.08
    符
    0.08
    wc
    0.08
     discussion
    0.08
    Activations Density 0.016%

    No Known Activations