© 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. 13760
    Prev
    Next
    INDEX
    Explanations

    evaluative adjectives

    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
    åĴĮæĶ¯æĮģ
    -0.18
    пÑĢоÑĦеÑģÑģионал
    -0.18
    åĴĮåıijå±ķ
    -0.18
     ìĿ´ìłľ
    -0.18
     Sheets
    -0.18
    aget
    -0.17
    åĶĨ
    -0.17
    åIJĮåŁİ
    -0.17
    çĭłæĬĵ
    -0.17
    쪼
    -0.17
    POSITIVE LOGITS
    缸çĪ±
    0.21
    -to
    0.20
     vs
    0.19
    è¯
    0.19
    æŃĮ声
    0.18
    би
    0.18
    èĦijè¢ĭ
    0.18
    è¡Įä¸ļçļĦ
    0.18
    ist
    0.18
    年人
    0.18
    Activations Density 0.101%

    No Known Activations