© 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. 4853
    Prev
    Next
    INDEX
    Explanations

    Search by name or array

    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
    ç«
    -0.09
     оÑĤз
    -0.09
    _transient
    -0.09
    ond
    -0.09
    çŁ³åĮĸ
    -0.08
     stiff
    -0.08
    æĭĪ
    -0.08
    å·¡æŁ¥
    -0.08
    åģļä¸ĢäºĽ
    -0.08
    åij»
    -0.08
    POSITIVE LOGITS
     bore
    0.10
    èĦIJ
    0.09
    代åĬŀ
    0.09
    sis
    0.08
    æ¢Ĺ
    0.08
    umps
    0.08
    Anywhere
    0.08
    符åIJĪæĿ¡ä»¶
    0.08
    UMP
    0.08
     OR
    0.08
    Activations Density 0.182%

    No Known Activations