© 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. 11957
    Prev
    Next
    INDEX
    Explanations

    Imports and imported

    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
    æĶ¯éħį
    -0.24
    lyph
    -0.19
    ysz
    -0.19
    å¾ĹæĦı
    -0.19
    _alias
    -0.19
     gan
    -0.18
    GAN
    -0.18
    oir
    -0.18
    åĨĻåĩº
    -0.18
    анÑĤ
    -0.18
    POSITIVE LOGITS
    å¼ķè¿Ľ
    0.38
    è¯ij
    0.30
    æľ¬åľ°
    0.25
    è¿Ľåı£
    0.25
     Imported
    0.23
    èŃ
    0.23
     Imports
    0.23
    æݥ轨
    0.23
    æľ¬åľŁ
    0.23
    å¤ĸæĿ¥
    0.22
    Activations Density 0.195%

    No Known Activations