© 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. 20292
    Prev
    Next
    INDEX
    Explanations

    .css file references

    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
    åĹ·
    -0.09
    èĭį
    -0.09
    æķijæĬ¤
    -0.09
    beat
    -0.09
    çĻ»ä¸Ĭ
    -0.08
    å¨ģ
    -0.08
    ä¸Ńæŀ¢
    -0.08
    ÑĪÑĥ
    -0.08
    Smarty
    -0.08
    /providers
    -0.08
    POSITIVE LOGITS
    illard
    0.09
    çłĶ究éĻ¢
    0.09
    æ³
    0.09
    èĴ»
    0.09
    dom
    0.08
    èĤ¡æĿĥæĬķèµĦ
    0.08
    éĩijèŀįå¸Ĥåľº
    0.08
    аÑĩ
    0.08
    éĩĮç¨ĭ
    0.08
    inding
    0.08
    Activations Density 0.618%

    No Known Activations