© 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. 13639
    Prev
    Next
    INDEX
    Explanations

    automatically creates or finds

    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
    è¢Ĵ
    -0.21
     Salah
    -0.20
    .stringValue
    -0.20
    laden
    -0.20
     Humb
    -0.19
    strument
    -0.19
    è´»
    -0.19
    orget
    -0.19
    ýt
    -0.19
    è°Ķ
    -0.19
    POSITIVE LOGITS
     automáticamente
    0.37
     automatically
    0.35
    èĩªåĬ¨
    0.31
    ç»Ļä½ł
    0.30
    å¸®ä½ł
    0.30
    é»ĺ认
    0.29
    èĩªåĭķ
    0.27
    autom
    0.27
     авÑĤомаÑĤ
    0.26
    AUTO
    0.24
    Activations Density 0.242%

    No Known Activations