© 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. 14033
    Prev
    Next
    INDEX
    Explanations

    storage or floor space

    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
    家éŨåı£
    -0.24
    lix
    -0.20
    Tre
    -0.20
     rod
    -0.20
    æķħ乡
    -0.19
    angen
    -0.19
    preload
    -0.19
    æīĵåĩ»
    -0.18
    ç¼Ń
    -0.18
    rod
    -0.18
    POSITIVE LOGITS
    æĶ¹éĢł
    0.30
    åĪĨåī²
    0.27
    æīĵéĢļ
    0.27
    转åıĺ
    0.26
    æĭĨ
    0.26
    缸éĤ»
    0.24
    æł¼å±Ģ
    0.24
    åIJĪ并
    0.24
    ặ
    0.23
    åĪĴåĪĨ
    0.23
    Activations Density 0.132%

    No Known Activations