© 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. 19308
    Prev
    Next
    INDEX
    Explanations

    the the executive

    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
     nonetheless
    -0.09
    äºĭå®ľ
    -0.09
    tel
    -0.09
    çļĦåŃ¦ä¹ł
    -0.09
    å¹³æĿ¿
    -0.09
    çļĦåį±å®³
    -0.09
    ynth
    -0.08
    angu
    -0.08
    è¿ĺ以为
    -0.08
    åĮĹéĥ¨
    -0.08
    POSITIVE LOGITS
    /or
    0.15
    /OR
    0.10
    导åIJij
    0.10
    &nbsp
    0.09
    mis
    0.09
    举
    0.08
    æĭĦ
    0.08
    éķ¿çĽ¸
    0.08
    etting
    0.08
     Glory
    0.08
    Activations Density 0.140%

    No Known Activations