© 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. 15819
    Prev
    Next
    INDEX
    Explanations

    cities; programming headers

    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
     ÐIJлекÑģан
    -0.24
    ä¸įä¸Ĭ
    -0.23
    夹
    -0.22
     gross
    -0.21
     à¹Ģมษ
    -0.21
    çĤ¹è¯Ħ
    -0.21
    flat
    -0.21
    ç»ĵæĿŁåIJİ
    -0.20
    ä¾Ľ
    -0.20
     tail
    -0.19
    POSITIVE LOGITS
    åĩºçīĪ社
    0.22
    åıijè¡Į
    0.20
    åħ¬å¼Ģåıijè¡Į
    0.20
    åIJ½
    0.19
     Bow
    0.19
    å¹´çĶ±
    0.19
    istorical
    0.19
    publisher
    0.19
     помеÑī
    0.19
    ublish
    0.18
    Activations Density 0.016%

    No Known Activations