© 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. 15085
    Prev
    Next
    INDEX
    Explanations

    use of this

    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
    ovich
    -0.21
    عاش
    -0.19
    aurus
    -0.19
    OV
    -0.18
    åĪ°å¤Ħ
    -0.18
    è°¢è°¢ä½ł
    -0.18
    æħ¢æħ¢åľ°
    -0.18
    oken
    -0.18
    æŶåĪ»
    -0.18
    ric
    -0.18
    POSITIVE LOGITS
    ç§ģèĩª
    0.24
    è°ģéĥ½
    0.22
    æĵħ
    0.21
    è¡Į为
    0.20
    åį³ä½¿æĺ¯
    0.20
    ä¸į符
    0.20
    ëĭ´
    0.20
    请èģĶç³»
    0.19
    æ¶īåıĬ
    0.19
    ä¼ģåĽ¾
    0.19
    Activations Density 0.056%

    No Known Activations