© 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. 20169
    Prev
    Next
    INDEX
    Explanations

    simply/just followed by an action

    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
    ä¸įåIJĥ
    -0.10
    åĩĮæĻ¨
    -0.10
    è·ijäºĨ
    -0.09
    å¹´å¤ľ
    -0.09
    oux
    -0.09
     Lima
    -0.08
    åįĪ
    -0.08
    åıĪ被
    -0.08
    abal
    -0.08
    大åѦçĶŁ
    -0.08
    POSITIVE LOGITS
    æĮīä¸ĭ
    0.10
    omba
    0.09
    åıªéľĢ
    0.09
    æľĽåİ»
    0.09
    åıªéľĢè¦ģ
    0.09
    豪
    0.09
    omb
    0.09
    åıijå±ķéĺ¶æ®µ
    0.08
    å»ºåĽ½
    0.08
     اÙĦØŃر
    0.08
    Activations Density 0.019%

    No Known Activations