© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51900
    Prev
    Next
    INDEX
    Explanations

    club career

    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
    åħ®
    -0.10
    oir
    -0.10
    azes
    -0.10
    ÙĤ
    -0.10
    ureka
    -0.09
    ÑģÑı
    -0.09
     Spicer
    -0.09
    åŁºè°ĥ
    -0.08
    OrDefault
    -0.08
    İ
    -0.08
    POSITIVE LOGITS
    bing
    0.13
    åĴĮ个人
    0.11
    zilla
    0.11
    mates
    0.11
    pedia
    0.10
    ä¸įä¸Ĭ
    0.10
    mate
    0.10
    bers
    0.09
    ï¸
    0.09
    bable
    0.09
    Activations Density 0.025%

    No Known Activations