© 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. 15994
    Prev
    Next
    INDEX
    Explanations

    TCP/IP connections

    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
    äºĮ代
    -0.21
     tort
    -0.18
    ful
    -0.17
    èĢģ人家
    -0.17
    zel
    -0.17
    们
    -0.17
    åĭĥåĭĥ
    -0.16
    iliation
    -0.16
    ocoder
    -0.16
    èĪħ
    -0.16
    POSITIVE LOGITS
    /IP
    0.27
    ðŁı»
    0.17
    à¹Į
    0.17
    ÑĮÑİ
    0.17
    ë§IJ
    0.16
    /ip
    0.16
     trÆ°á»Łng
    0.15
     fame
    0.15
    ìĹ´
    0.15
    çĶŁæĢķ
    0.15
    Activations Density 0.010%

    No Known Activations