© 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. 11836
    Prev
    Next
    INDEX
    Explanations

    visiting places and things

    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
    çķĻä½ı
    -0.18
     Geile
    -0.17
    ewan
    -0.17
    lease
    -0.17
    iac
    -0.17
     иÑģполÑĮзование
    -0.17
    ument
    -0.17
     дело
    -0.16
    mÃ¤ÃŁig
    -0.16
    hift
    -0.16
    POSITIVE LOGITS
    æħ°éĹ®
    0.23
    è¿ĩçļĦ
    0.20
    ê°Ŀ
    0.20
    çĦī
    0.18
    伤çĹħ
    0.18
    ä¸Ģè¶Ł
    0.18
    人家
    0.18
    çľĭæľĽ
    0.17
    isting
    0.17
    tion
    0.17
    Activations Density 0.034%

    No Known Activations