© 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. 22089
    Prev
    Next
    INDEX
    Explanations

    describing or defining

    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
    æĮĩ导æĦıè§ģ
    -0.09
    iez
    -0.09
    象
    -0.09
    yt
    -0.09
    ç®IJ
    -0.09
    åįķçĭ¬
    -0.09
    åIJĮç±»
    -0.08
    ýt
    -0.08
    åħ¶å®ĥéĹ®é¢ĺ
    -0.08
    umn
    -0.08
    POSITIVE LOGITS
    è½®å»ĵ
    0.09
    ç»į
    0.09
     intent
    0.08
     descri
    0.08
     describe
    0.08
     cir
    0.08
    pee
    0.08
    é«
    0.08
    æııè¿°
    0.08
     lag
    0.08
    Activations Density 0.377%

    No Known Activations