© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11254
    Prev
    Next
    INDEX
    Explanations

    schema, $schema, XS Subs

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Haut
    -0.21
    overe
    -0.19
    igu
    -0.19
    chemes
    -0.19
    æľīæĦıæĢĿçļĦ
    -0.18
    _TUN
    -0.17
     dor
    -0.17
    å°»
    -0.17
    æĥ³æī¾
    -0.17
    çŁ¥åIJį度
    -0.17
    POSITIVE LOGITS
     sentimental
    0.19
    é²Ł
    0.19
    æĢĿæĥ³æĶ¿æ²»
    0.19
    çķĻå®Ī
    0.19
    èĨĽ
    0.18
    æŀŀ
    0.18
    sten
    0.17
    è¿IJ转
    0.17
    iden
    0.17
    äºīåIJµ
    0.17
    Activations Density 0.002%

    No Known Activations