© 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. 39002
    Prev
    Next
    INDEX
    Explanations

    skills training and techniques

    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
    åįĬ天
    -0.10
    ided
    -0.10
    çĤī
    -0.09
    ilon
    -0.09
    riad
    -0.09
    åĸĩåıŃ
    -0.09
    æĮ¯å¥ĭ
    -0.09
    éŀŃ
    -0.09
    缸åħ³åĨħ容
    -0.08
    éĺļ
    -0.08
    POSITIVE LOGITS
    æĬĢå·§
    0.14
     skills
    0.13
    æĬĢèĥ½
    0.12
    skills
    0.11
     techniques
    0.10
    æĬĢèīº
    0.10
     Skills
    0.09
    ä¼İ
    0.09
     coping
    0.09
    _skills
    0.09
    Activations Density 0.095%

    No Known Activations