© 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. 52539
    Prev
    Next
    INDEX
    Explanations

    knowingly collect personal

    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¿ŁåĪ°
    -0.09
     terror
    -0.09
    åĪ°è´¦
    -0.09
    /aws
    -0.08
    èĮĤ
    -0.08
    æĮ¨
    -0.08
    åĻ¤
    -0.08
    çļĦ姿æĢģ
    -0.08
    èľ±
    -0.08
     limp
    -0.08
    POSITIVE LOGITS
    积累
    0.10
    INI
    0.10
    éĴī
    0.10
    PURE
    0.09
    ayed
    0.09
    unj
    0.09
    å¿ĥæĻº
    0.09
     Expanded
    0.09
    .Inner
    0.09
    ikal
    0.09
    Activations Density 0.017%

    No Known Activations