© 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. 11715
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
    à¸Ħà¸ĵะà¸ģรรม
    -0.29
    à¹Ĥรà¸ĩà¸ŀยา
    -0.27
    -d
    -0.25
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    -0.25
    ä½ķ
    -0.24
     unt
    -0.24
     det
    -0.24
     r
    -0.24
    åľ°
    -0.24
     res
    -0.24
    POSITIVE LOGITS
     strapon
    0.28
    åľ¨çݩ家ä¸Ń
    0.26
     shemale
    0.25
    iếc
    0.25
    iéndo
    0.25
     milfs
    0.24
    ERSHEY
    0.23
    çĮ¾
    0.23
    ernetes
    0.23
     fkk
    0.23
    Activations Density 0.034%

    No Known Activations