© 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. 52304
    Prev
    Next
    INDEX
    Explanations

    world of

    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
    ean
    -0.10
    QUE
    -0.09
    chos
    -0.08
    ìĤ¬íķŃ
    -0.08
    ees
    -0.08
    æĸ¯çī¹
    -0.08
    tees
    -0.08
    que
    -0.08
    åĤį
    -0.08
    edImage
    -0.08
    POSITIVE LOGITS
    liness
    0.16
    igner
    0.12
    inar
    0.10
    çŀ©
    0.10
    åĴĮåľ°åĮº
    0.10
    ä»¥äººä¸ºæľ¬
    0.10
    istically
    0.10
    尽头
    0.09
    icher
    0.09
    箪
    0.09
    Activations Density 0.063%

    No Known Activations