© 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. 15816
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases and conjunctions

    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
    çĦ¶èĢĮ
    -0.20
    however
    -0.19
     however
    -0.19
    ãģĦãģŁãģłãģį
    -0.18
    æ·¡æ°´
    -0.18
    åĴĮåľ°åĮº
    -0.18
    éĻ¸
    -0.17
     однако
    -0.17
     fontStyle
    -0.17
     denn
    -0.17
    POSITIVE LOGITS
     ìĿ´ë¥¼
    0.25
    ãģĿãĤĮãģĮ
    0.23
    ãģĿãĤĮãĤĴ
    0.23
     thereof
    0.23
    å®ĥ
    0.22
     ê·¸ê²ĥìĿĦ
    0.22
     importantly
    0.21
    æĥħåĨµè¿Ľè¡Į
    0.20
    ãģĿãĤĮãģ«
    0.20
    å°Ĩåħ¶
    0.20
    Activations Density 0.113%

    No Known Activations