© 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. 15442
    Prev
    Next
    INDEX
    Explanations

    patent applications and scientific discoveries

    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
    æģ¨
    -0.22
    æ¦Ĩ
    -0.21
    çł´ç¢İ
    -0.20
    éĤ®ä»¶
    -0.20
    æķ²
    -0.19
    lsi
    -0.19
    inati
    -0.19
     seat
    -0.19
    fold
    -0.18
    å¹£
    -0.18
    POSITIVE LOGITS
    avy
    0.21
    hung
    0.21
     faithful
    0.20
     oxy
    0.20
     cog
    0.19
     Param
    0.19
     "(\<
    0.19
     Provid
    0.19
    elon
    0.19
    温æļĸ
    0.19
    Activations Density 0.028%

    No Known Activations