© 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. 20303
    Prev
    Next
    INDEX
    Explanations

    ticket office, sales, booking

    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
    éĻħ
    -0.13
    ðŁı»
    -0.11
    /front
    -0.10
    å¿ĥè·³
    -0.10
    ä½ĵè´´
    -0.10
    éļĽ
    -0.09
    íħį
    -0.09
    éĺ»åĬĽ
    -0.09
    æĸ¯é¡¿
    -0.09
    /includes
    -0.09
    POSITIVE LOGITS
    ting
    0.15
    æł·çļĦ
    0.10
     Burr
    0.10
    preter
    0.09
    orial
    0.09
    elsen
    0.09
    ing
    0.09
    æĬ½å¥ĸ
    0.09
    edly
    0.09
    shal
    0.08
    Activations Density 0.008%

    No Known Activations