© 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. 13746
    Prev
    Next
    INDEX
    Explanations

    astronomer, observing, amateur astronomy

    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
     наÑĢко
    -0.22
    oha
    -0.22
    -decoration
    -0.22
    ðŁıĹ
    -0.21
    piler
    -0.21
     Accent
    -0.21
    .Health
    -0.21
    itra
    -0.21
    _AdjustorThunk
    -0.21
    ontology
    -0.21
    POSITIVE LOGITS
    ç§ijæĻ®
    0.34
    ä¸ļä½Ļ
    0.33
    è§Ĥæµĭ
    0.32
    åħīåѦ
    0.29
    天æĸĩ
    0.28
    æľĽ
    0.27
     amateur
    0.26
    太éĺ³
    0.25
     Amateur
    0.25
     amateurs
    0.24
    Activations Density 0.033%

    No Known Activations