© 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. 20383
    Prev
    Next
    INDEX
    Explanations

    directed by

    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
    à¸ĺรรม
    -0.09
    MES
    -0.09
    æī«
    -0.09
    aters
    -0.09
    steller
    -0.08
    tera
    -0.08
    管çIJĨä¸Ńå¿ĥ
    -0.08
    itary
    -0.08
    asad
    -0.08
    æĹłåģ¿
    -0.08
    POSITIVE LOGITS
    ial
    0.13
    èĢħçļĦ
    0.10
    大åĴĸ
    0.09
    yer
    0.09
    çıŃåŃIJ
    0.09
    ially
    0.09
    åħ¼
    0.09
    åĬ©çIJĨ
    0.08
     Pax
    0.08
    èīºæľ¯
    0.08
    Activations Density 0.025%

    No Known Activations