© 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. 50984
    Prev
    Next
    INDEX
    Explanations

    academic programs and courses

    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
    åĢ¾
    -0.11
    å¢ĥ
    -0.10
    交éĢļå®īåħ¨
    -0.10
    äºĮ线
    -0.09
    交éĢļ
    -0.09
    æijĶ
    -0.08
    claims
    -0.08
    irma
    -0.08
    åĺī宾
    -0.08
     Century
    -0.08
    POSITIVE LOGITS
    åѦä½į
    0.12
     degree
    0.11
    /master
    0.11
    -degree
    0.11
     programs
    0.11
     courses
    0.10
    åħ¨æĹ¥åĪ¶
    0.10
    degree
    0.10
    masters
    0.10
     degrees
    0.10
    Activations Density 0.112%

    No Known Activations