© 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. 36333
    Prev
    Next
    INDEX
    Explanations

    `.out` or URL patterns

    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
    è¿Ļä¹Ī说
    -0.09
    åIJĪ
    -0.09
    èĻij
    -0.09
    راج
    -0.09
    å¸
    -0.09
    ä½ıåĿĢ
    -0.09
    è¤
    -0.09
    ics
    -0.09
     ÐijеÑģ
    -0.08
    è¡Įä¸ļåıijå±ķ
    -0.08
    POSITIVE LOGITS
    æĬ¥åĪĬ
    0.11
    æŁij
    0.09
    åį«è§Ĩ
    0.09
    èĥĮ
    0.09
    uo
    0.09
    uous
    0.08
    dj
    0.08
    çļĦå¿ĥæĥħ
    0.08
    hou
    0.08
    çIJĨç§ij
    0.08
    Activations Density 0.269%

    No Known Activations