© 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. 10740
    Prev
    Next
    INDEX
    Explanations

    SELECT statements

    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
    iar
    -0.21
    åĪĩå°Ķ
    -0.20
    æ®ĩ
    -0.19
    ktop
    -0.19
    æľ¦
    -0.19
    åIJ»
    -0.19
    èĥ
    -0.19
    alem
    -0.18
    linger
    -0.18
    zf
    -0.18
    POSITIVE LOGITS
     statement
    0.28
     statements
    0.24
    åIJİçļĦ
    0.23
    è¯Ń
    0.20
    çļĦ缮çļĦ
    0.20
    OrUpdate
    0.20
    å¼ıçļĦ
    0.19
    åıijçĶŁåľ¨
    0.19
    å¾½
    0.19
    è¿ĩçļĦ
    0.18
    Activations Density 0.585%

    No Known Activations