© 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. 6567
    Prev
    Next
    INDEX
    Explanations

    trendy, hip, or hipster

    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
    vat
    -0.10
    åĽ½å®¶æłĩåĩĨ
    -0.09
    åĪĢ
    -0.09
    褴
    -0.09
    ä¸īåĽ½
    -0.09
    åĬĽéĩı
    -0.09
    å¹ķ
    -0.09
    apons
    -0.09
    веÑĢ
    -0.08
    æ²īéĩį
    -0.08
    POSITIVE LOGITS
     hip
    0.13
    çĻ½é¢Ĩ
    0.13
    é«ĺ端
    0.12
    ç²¾èĭ±
    0.12
    é«ĺç´łè´¨
    0.11
     trendy
    0.11
    æŶ髦
    0.11
    é«ĺ级
    0.10
    hipster
    0.10
     Hip
    0.10
    Activations Density 0.141%

    No Known Activations