© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53936
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
    ä¸įåĥı
    -0.11
    ç´¯äºĨ
    -0.09
    轺
    -0.09
    achs
    -0.09
    hof
    -0.09
    اÙĦتز
    -0.09
    è¿Ļæīį
    -0.09
    è¿Ļ段æŶéĹ´
    -0.09
    ä¸įåĪĨ
    -0.09
    ordo
    -0.08
    POSITIVE LOGITS
    è¿Ļä¸Ģ天
    0.11
    å·¦åı³
    0.11
    illion
    0.09
     onwards
    0.08
    /month
    0.08
     enr
    0.08
     Shib
    0.08
    اظ
    0.08
    \Unit
    0.08
    -election
    0.08
    Activations Density 0.086%

    No Known Activations