© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10539
    Prev
    Next
    INDEX
    Explanations

    furry things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    íĴĪ
    -0.23
    ëģĶ
    -0.20
    ë¥ł
    -0.17
    sWith
    -0.17
    oron
    -0.16
    Ñģ
    -0.15
    vre
    -0.15
    ubb
    -0.15
    ev
    -0.15
    eve
    -0.15
    POSITIVE LOGITS
    说æĺ¯
    0.29
    thest
    0.22
    istic
    0.20
    teenth
    0.19
    balls
    0.18
    ments
    0.18
    ÙĨÙĪ
    0.17
    إص
    0.16
    gies
    0.16
    /body
    0.16
    Activations Density 0.008%

    No Known Activations