© 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. 9819
    Prev
    Next
    INDEX
    Explanations

    qualities and abstract nouns

    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
    egan
    -0.09
    icht
    -0.09
    è¦Ĩ
    -0.09
    æľīèī²
    -0.09
    edom
    -0.09
    LÄ°
    -0.08
    XmlElement
    -0.08
    棱
    -0.08
    веÑģ
    -0.08
    acceptable
    -0.08
    POSITIVE LOGITS
    åºĬä¸Ĭ
    0.11
     nature
    0.10
    è¿Ļå¼ł
    0.10
    nature
    0.10
    æĢ
    0.10
    åĢ¨
    0.10
    çŧ
    0.09
    渺
    0.09
    æ¡´
    0.09
    è¿Ļä¹Ī说
    0.09
    Activations Density 0.145%

    No Known Activations