© 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. 51198
    Prev
    Next
    INDEX
    Explanations

    depending on

    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
    MimeType
    -0.09
     cdr
    -0.09
    ä¹ŁçŁ¥éģĵ
    -0.08
    æĩĤäºĭ
    -0.08
     Campos
    -0.08
    ader
    -0.08
    ä¸įæĺİçĻ½
    -0.08
    =-=-=-=-=-=-=-=-
    -0.08
    éľľ
    -0.08
    arks
    -0.08
    POSITIVE LOGITS
    äºĮèĢħ
    0.14
    两èĢħ
    0.13
    åIJİèĢħ
    0.13
    åīįèĢħ
    0.13
    åıĸåĨ³äºİ
    0.12
    åĽłä¸ºä»ĸ们
    0.12
    åıĸåĨ³
    0.12
    åŃ°
    0.11
     whichever
    0.10
     depending
    0.10
    Activations Density 0.075%

    No Known Activations