© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15319
    Prev
    Next
    INDEX
    Explanations

    code method prefixes

    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
    好ä¸į好
    -0.17
    åij¨å¹´
    -0.17
     Peb
    -0.17
    erno
    -0.17
    osti
    -0.17
    å®ĺæĸ¹
    -0.17
    dato
    -0.17
    een
    -0.16
    rost
    -0.16
     ReturnValue
    -0.16
    POSITIVE LOGITS
    /-
    0.25
    /+
    0.19
    bidden
    0.19
    cratch
    0.16
    _safe
    0.16
    кл
    0.16
    credible
    0.16
     grave
    0.16
    #+#+
    0.16
    åĭ¿
    0.16
    Activations Density 0.619%

    No Known Activations