© 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. 38411
    Prev
    Next
    INDEX
    Explanations

    skills and expertise

    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
    æĬ¢åįł
    -0.10
     Presidents
    -0.09
    asher
    -0.09
    hip
    -0.09
     IST
    -0.08
    ç§ķ
    -0.08
    atives
    -0.08
    bum
    -0.08
    ocular
    -0.08
    åį°è±¡
    -0.08
    POSITIVE LOGITS
     expertise
    0.17
    æĬĢèĥ½
    0.15
     skills
    0.15
    çī¹éķ¿
    0.15
     Skills
    0.13
     talents
    0.13
    skills
    0.12
    expert
    0.12
    ãĤ¹ãĤŃãĥ«
    0.11
    ä¸ĵä¸ļçŁ¥è¯Ĩ
    0.11
    Activations Density 0.065%

    No Known Activations