© 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. 54530
    Prev
    Next
    INDEX
    Explanations

    government offices

    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
    asar
    -0.09
    lica
    -0.09
    mai
    -0.08
    itized
    -0.08
    .Iterator
    -0.08
    enze
    -0.08
    好人
    -0.08
    é£İæ°Ķ
    -0.08
    è¡Įä¸ļçļĦ
    -0.08
    _restart
    -0.08
    POSITIVE LOGITS
    åĴĮåľ°åĮº
    0.11
    å¹³æŶ
    0.10
    æ²Ļåıij
    0.09
    ä¸ĢåĪ»
    0.09
    ariat
    0.09
    çĵľ
    0.09
    åİħ
    0.09
    æ±Ľ
    0.09
    PM
    0.09
    çĶļ
    0.08
    Activations Density 0.042%

    No Known Activations