© 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. 51560
    Prev
    Next
    INDEX
    Explanations

    fruit and fruit-related terms

    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
    Ñģли
    -0.10
    /licenses
    -0.10
    æºĥ
    -0.10
    ValuePair
    -0.10
    alous
    -0.10
    ç¼¢
    -0.10
    åŃĹåı·
    -0.10
     Kushner
    -0.09
    ÑĪение
    -0.09
    æµħ
    -0.09
    POSITIVE LOGITS
    INESS
    0.08
    æģ¶
    0.08
    åĬŁåĬ³
    0.08
    å¥ĩ迹
    0.08
    oman
    0.08
     Hin
    0.07
    é«ĺåĩº
    0.07
    æĺİå¹´
    0.07
    claim
    0.07
    cale
    0.07
    Activations Density 0.001%

    No Known Activations