© 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. 14400
    Prev
    Next
    INDEX
    Explanations

    restaurants and cafes

    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
    forme
    -0.22
    gaard
    -0.21
    ળ
    -0.20
    opoulos
    -0.19
    毽
    -0.19
    å·´å·´
    -0.19
    æİ¥åĬĽ
    -0.19
    åĽļ
    -0.18
     hã
    -0.18
     comb
    -0.18
    POSITIVE LOGITS
    便åĪ©
    0.24
     amenities
    0.24
    éħįå¥Ĺ设æĸ½
    0.22
    åħ¬åħ±æľįåĬ¡
    0.22
    éĻĦè¿ij
    0.22
     ÙĤرÙĬب
    0.21
    æŃ¥è¡Į
    0.21
    设æĸ½
    0.20
    丰å¯Į
    0.20
    河边
    0.20
    Activations Density 0.014%

    No Known Activations