© 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. 38442
    Prev
    Next
    INDEX
    Explanations

    numbers and dollar amounts

    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
    为æĬĵ
    -0.10
    æĵħ
    -0.10
    åı²ä¸ĬæľĢ
    -0.09
    çİĩ为
    -0.09
    éĴ¤
    -0.09
    åĪ·
    -0.09
    cljs
    -0.08
    åįģ足
    -0.08
    åĮĢ
    -0.08
    åıįå¤į
    -0.08
    POSITIVE LOGITS
    èIJ½åĪ°
    0.08
    èĭĩ
    0.08
    itals
    0.08
    æŦ
    0.08
    anh
    0.08
    æĪIJ
    0.08
    andon
    0.07
    ä¸īåįĥ
    0.07
    igator
    0.07
    诤
    0.07
    Activations Density 0.055%

    No Known Activations