© 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. 16241
    Prev
    Next
    INDEX
    Explanations

    journal of

    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
    åºĹåĨħ
    -0.22
    permanent
    -0.19
    ä½ıæĪ¿åħ¬ç§¯
    -0.19
    æĪĸå¤ļæĪĸ
    -0.19
    é«»
    -0.18
    å¹»
    -0.18
    äºĴèģĶäºĴéĢļ
    -0.18
    æ»ł
    -0.18
    FACT
    -0.18
    é£ı
    -0.18
    POSITIVE LOGITS
    æľŁåĪĬ
    0.27
     journals
    0.23
     subscribed
    0.22
     journal
    0.22
     publishes
    0.22
     prestige
    0.21
    楹
    0.21
     жÑĥÑĢнал
    0.21
    åĪĬçī©
    0.20
     subscriptions
    0.20
    Activations Density 0.026%

    No Known Activations