© 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. 23071
    Prev
    Next
    INDEX
    Explanations

    country club

    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
    æĿijåŃIJ
    -0.11
    æľ¬åĽ½
    -0.10
    èĥ½çľĭåĩº
    -0.10
    icit
    -0.10
    主è¦ģåĨħ容
    -0.10
    ç´łè´¨æķĻèĤ²
    -0.10
    rah
    -0.10
    çģ¿
    -0.09
    åīįæīĢ
    -0.09
    豸
    -0.09
    POSITIVE LOGITS
    amp
    0.09
    ledge
    0.08
    iegel
    0.08
    大家åĪĨ享
    0.08
    ahoma
    0.08
    eut
    0.08
     Bulldogs
    0.08
    aminer
    0.08
    tog
    0.08
    еннÑĥÑİ
    0.08
    Activations Density 0.010%

    No Known Activations