© 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. 7658
    Prev
    Next
    INDEX
    Explanations

    combined with

    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
    æĹ¶ä»£ä¸ŃåĽ½
    -0.10
    éģĹæĨ¾
    -0.10
    çªģåĩ»
    -0.10
    èĩ´çĶµ
    -0.10
    人å¿ĥ
    -0.09
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.09
    群éĩĮ
    -0.09
    Æ°ng
    -0.09
    åIJįè¯į
    -0.09
    èĬ«
    -0.09
    POSITIVE LOGITS
    åĨįåĬłä¸Ĭ
    0.15
    åĬłä¸Ĭ
    0.13
    åĬłä¹ĭ
    0.11
    åİŁæľīçļĦ
    0.10
    åıĪæľī
    0.10
     Fur
    0.09
    fact
    0.08
     plus
    0.08
    åıĪèĥ½
    0.08
     viá»ĩc
    0.08
    Activations Density 0.024%

    No Known Activations