© 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. 19684
    Prev
    Next
    INDEX
    Explanations

    automobile manufacturers and companies

    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»į
    -0.11
    èĢģ人
    -0.09
    åħĪæĬĬ
    -0.09
    çľĭä¸įåĪ°
    -0.08
     Eternal
    -0.08
    ä½Ĩä¹Ł
    -0.08
    éĺŁéķ¿
    -0.08
    arel
    -0.08
    åĴķ
    -0.08
    å¯ĩ
    -0.08
    POSITIVE LOGITS
    æģ¶åĬ£
    0.10
     tắt
    0.09
    羿
    0.08
     Walters
    0.08
    ubs
    0.08
    ÑģÑĤавка
    0.08
    åİĨæŶ
    0.08
    Bat
    0.08
    æĤ´
    0.08
    bat
    0.08
    Activations Density 0.014%

    No Known Activations