© 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. 61540
    Prev
    Next
    INDEX
    Explanations

    Unity asset importers

    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
    å®ŀæĸ½
    -0.10
    ä¸Ģè¡Į
    -0.09
     Salem
    -0.09
    è¨Ģè¡Į
    -0.09
     implementing
    -0.09
    hardware
    -0.08
     implementations
    -0.08
    æŃĩ
    -0.08
    implement
    -0.08
    åĬ¨æīĭ
    -0.08
    POSITIVE LOGITS
    æīĵåĮħ
    0.10
    è²Ĥ
    0.09
    åIJIJ
    0.09
    游客
    0.09
    .low
    0.09
    çĽĸ
    0.09
     chew
    0.09
    æŀķ
    0.08
    ä¸Ŀ绸
    0.08
    åĴĮåıijå±ķ
    0.08
    Activations Density 0.215%

    No Known Activations