© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10648
    Prev
    Next
    INDEX
    Explanations

    streets

    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
    å¢ĥçķĮ
    -0.19
    ä»İä¸Ń
    -0.18
    两åıª
    -0.18
    åħ¶å®ĥéĹ®é¢ĺ
    -0.18
    èĪĮ头
    -0.18
    çŀ°
    -0.17
    åIJĦæĸ¹éĿ¢
    -0.17
     английÑģк
    -0.17
    owan
    -0.17
    åı¯çĪ±
    -0.17
    POSITIVE LOGITS
    æ·±å¤Ħ
    0.23
    acco
    0.21
    nier
    0.19
    harma
    0.19
     Shutterstock
    0.19
    nable
    0.18
    éĹ¹
    0.18
    uko
    0.18
    umes
    0.18
    uggy
    0.18
    Activations Density 0.024%

    No Known Activations