© 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. 32517
    Prev
    Next
    INDEX
    Explanations

    spending money wisely

    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
    è´¯
    -0.11
    åĬŁ
    -0.10
    (utf
    -0.10
    温æĥħ
    -0.09
    åĵ²
    -0.09
    åī¯ä½ľçĶ¨
    -0.09
     qb
    -0.09
    ç¨į
    -0.08
    /embed
    -0.08
    å¤ĸçķĮ
    -0.08
    POSITIVE LOGITS
    èĬ®
    0.10
    éĥ½å¾Ī
    0.09
     trá»įng
    0.09
    æĴĴ
    0.09
    å¿į
    0.09
     Lane
    0.08
    linger
    0.08
     spent
    0.08
    åIJĦ项
    0.08
     tantr
    0.08
    Activations Density 0.030%

    No Known Activations