© 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. 37320
    Prev
    Next
    INDEX
    Explanations

    Radcliffe names

    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
    çĶļ
    -0.10
    è¿«ä¸įåıĬå¾ħ
    -0.08
    çĶļèĩ³
    -0.08
    _STA
    -0.08
    å¾ĺ
    -0.08
    èį·èĬ±
    -0.08
    èĤĽ
    -0.07
    æѤç§į
    -0.07
    essim
    -0.07
    èħ¹æ³»
    -0.07
    POSITIVE LOGITS
    tro
    0.10
    à¹Ĥà¸Ĭ
    0.10
    èĪĢ
    0.09
    æ»Ķ
    0.09
    ISIBLE
    0.09
    ÙħÙĪÙĦ
    0.09
    ESCO
    0.09
    åĬ©æīĭ
    0.09
    ãģ©
    0.09
     Edwin
    0.08
    Activations Density 0.002%

    No Known Activations