© 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. 7196
    Prev
    Next
    INDEX
    Explanations

    pauses or * 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
    åijĬè¯īä»ĸ
    -0.09
    è£Ļ
    -0.09
    éģŃéģĩ
    -0.09
    DTV
    -0.09
    çĦ¯
    -0.09
    èľĩ
    -0.09
    åı¯è°ĵæĺ¯
    -0.09
    åĭ¤åĬ³
    -0.08
    åħ»èĤ²
    -0.08
    èĴ½
    -0.08
    POSITIVE LOGITS
    æīĭä¸Ń
    0.10
     referring
    0.09
    说å®Į
    0.08
    ä¸Ģæīĭ
    0.08
    å£°éŁ³
    0.08
    æīĭä¸ŃçļĦ
    0.08
    оÑģÑĮ
    0.08
    æĮĩåIJij
    0.08
    /student
    0.08
     &_
    0.08
    Activations Density 0.019%

    No Known Activations