© 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. 20954
    Prev
    Next
    INDEX
    Explanations

    product strategy or management

    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
     невоз
    -0.10
    èİŀ
    -0.09
    å¸ĸ
    -0.09
    _DECLS
    -0.09
    fv
    -0.09
     Drawer
    -0.09
    CRC
    -0.08
     comprom
    -0.08
    _SUM
    -0.08
    crc
    -0.08
    POSITIVE LOGITS
    åĴĮæĬĢæľ¯
    0.10
    åģļ强
    0.09
    ünd
    0.09
    åģļ大åģļ强
    0.09
    åĩĢåĪ©æ¶¦
    0.08
    ivities
    0.08
    å°ıåĮº
    0.08
    åĴĮæľįåĬ¡
    0.08
    éħĬ
    0.08
    ivity
    0.08
    Activations Density 0.032%

    No Known Activations