© 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. 8848
    Prev
    Next
    INDEX
    Explanations

    names ending in 'ern', 'erm', 'erg'

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.11
    ðŁı»
    -0.10
    æ·±è¿ľ
    -0.10
    åĦ¿
    -0.10
    agner
    -0.10
    rons
    -0.10
    áĥł
    -0.09
    serter
    -0.09
    åħĴ
    -0.09
    -------------↵
    -0.09
    POSITIVE LOGITS
    inal
    0.13
    aceous
    0.11
    ivals
    0.10
    è¾ĺ
    0.10
    ศาส
    0.10
    çļ¿
    0.10
    abouts
    0.09
    à¹Į
    0.09
    itecture
    0.09
    inals
    0.09
    Activations Density 0.460%

    No Known Activations