© 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. 21492
    Prev
    Next
    INDEX
    Explanations

    physical impact or event

    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§Ī
    -0.10
    çĶļ
    -0.09
    两岸
    -0.09
    uchs
    -0.09
    å¡«è¡¥
    -0.09
    缼ä¸ĸ
    -0.09
    utom
    -0.09
    _macros
    -0.08
    ÑĥлÑĮ
    -0.08
    alin
    -0.08
    POSITIVE LOGITS
    att
    0.10
    æĸ¹åľĨ
    0.10
    æĢģ度
    0.09
    æĬĺæī£
    0.09
    常æĢģåĮĸ
    0.08
    èµĤ
    0.08
    æĺ¯ä¸Ģä½į
    0.08
    æµģè¡Į
    0.08
    apas
    0.08
    èĩ§
    0.08
    Activations Density 0.006%

    No Known Activations