© 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. 2338
    Prev
    Next
    INDEX
    Explanations

    romance languages and ethnic groups

    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
    åIJİåĭ¤
    -0.10
    elho
    -0.09
    æĻ®æĥł
    -0.09
    lich
    -0.08
    容
    -0.08
    对æĸ¹
    -0.08
     Mold
    -0.08
    端æŃ£
    -0.08
     Www
    -0.08
    ustum
    -0.08
    POSITIVE LOGITS
    缸è§ģ
    0.11
    idar
    0.09
    setId
    0.09
    æ²»çIJĨä½ĵç³»
    0.09
    eries
    0.09
    éŃĪ
    0.09
    ç²²
    0.09
    æĵİ
    0.09
    ç²¾ç¥ŀ
    0.08
    夹
    0.08
    Activations Density 0.080%

    No Known Activations