© 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. 53082
    Prev
    Next
    INDEX
    Explanations

    post-game interview press or operative complications

    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
    PRI
    -0.11
    æł¡åĮº
    -0.10
    tober
    -0.09
    bsp
    -0.09
    åħļæł¡
    -0.09
     PRI
    -0.09
    udu
    -0.08
    å½±éĻ¢
    -0.08
    好äºĭ
    -0.08
    æī¿åĬŀ
    -0.08
    POSITIVE LOGITS
    å«Į
    0.11
    çĶ³è¯·äºº
    0.09
    æı¡æīĭ
    0.09
    é¦Ļ
    0.09
    æĬĦ
    0.09
    unik
    0.09
    è¿ĻæĿ¡
    0.09
    åIJ¹
    0.08
    anean
    0.08
    åľ°åĽ¾
    0.08
    Activations Density 0.027%

    No Known Activations