© 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. 38226
    Prev
    Next
    INDEX
    Explanations

    New York Yankees

    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
    äºij端
    -0.09
    åīįæīĢ
    -0.09
    edata
    -0.09
    ives
    -0.09
    ammad
    -0.08
    åĽ½å®¶æĪĺçķ¥
    -0.08
    ÌĢ
    -0.08
    ail
    -0.08
    麼
    -0.08
    人éĻħåħ³ç³»
    -0.08
    POSITIVE LOGITS
    æ·Ģ
    0.13
    佬
    0.11
     Sachs
    0.11
    -Russian
    0.10
    Ø°
    0.09
    cept
    0.09
    hof
    0.09
    quis
    0.09
     воÑĤ
    0.09
    æĹģ
    0.08
    Activations Density 0.005%

    No Known Activations