© 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. 11070
    Prev
    Next
    INDEX
    Explanations

    chemical terms, fatty acids, oleic acid

    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
    odo
    -0.19
    æ¶İ
    -0.19
    æĪIJåIJį
    -0.18
     Lent
    -0.18
    ToArray
    -0.18
    å¾Ĺ罪
    -0.18
    ãģĹãģ¾ãģĨ
    -0.17
    uvw
    -0.17
     tapes
    -0.17
    åĸĿéħĴ
    -0.17
    POSITIVE LOGITS
    itÃł
    0.19
    à¹Į
    0.18
     Ñģобой
    0.18
     PARTICULAR
    0.17
    URITY
    0.17
    ÑĤÑĮ
    0.17
    .Automation
    0.17
    igen
    0.17
    ãģ£ãģ±
    0.17
    饱满
    0.17
    Activations Density 0.041%

    No Known Activations