© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3023
    Prev
    Next
    INDEX
    Explanations

    shyness, slyness, or -ly/-ish endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    家åĸ»æĪ·æĻĵ
    -0.23
    ials
    -0.23
    dition
    -0.20
     quaternion
    -0.20
    alive
    -0.19
    丰ç¡ķ
    -0.19
     grosse
    -0.18
    好è¿IJ
    -0.18
    undle
    -0.18
     reli
    -0.18
    POSITIVE LOGITS
    ãģªãģĮãĤī
    0.25
    ingly
    0.25
    ish
    0.24
    ened
    0.23
    ðŁı»
    0.23
    ude
    0.23
    è¡·
    0.21
    _EXPR
    0.20
    ely
    0.20
    èĩ¾
    0.20
    Activations Density 0.003%

    No Known Activations