© 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. 21380
    Prev
    Next
    INDEX
    Explanations

    -era, -ians, -aurus, -atie

    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
    ãĢħ
    -0.10
    æŶéĹ´åĨħ
    -0.09
    åĪ°æľĢåIJİ
    -0.09
    è§ĴèIJ½
    -0.09
    ä¹Łä¸įæĥ³
    -0.09
    å±±åİ¿
    -0.09
    ially
    -0.09
    ÑĩаÑģ
    -0.09
     importantly
    -0.08
    OfFile
    -0.08
    POSITIVE LOGITS
    -era
    0.12
    ians
    0.09
    apas
    0.09
    adays
    0.09
    odore
    0.08
    æŀ³
    0.08
    edo
    0.08
    aurus
    0.08
    ä¸Ńå°ıåŀĭ
    0.08
    atie
    0.08
    Activations Density 0.497%

    No Known Activations