© 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. 38864
    Prev
    Next
    INDEX
    Explanations

    opening quotation marks

    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
    çĭ¸
    -0.11
    åıijå±ķæĪĺçķ¥
    -0.10
    å·§åIJĪ
    -0.10
    ssc
    -0.09
    æªĢ
    -0.09
    -found
    -0.09
     gubern
    -0.09
    æģ«
    -0.09
    entes
    -0.09
    çļ²
    -0.09
    POSITIVE LOGITS
    æŶåĪ»
    0.09
    ä¸ĢåĪ»
    0.09
    çļĦ强大
    0.08
    夫
    0.08
    åĨħå¿ĥçļĦ
    0.08
    åºľ
    0.08
    ula
    0.07
    gro
    0.07
    ä¸Ĭåīį
    0.07
    æĪ·åı£
    0.07
    Activations Density 0.044%

    No Known Activations