© 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. 16851
    Prev
    Next
    INDEX
    Explanations

    pair of

    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
    iT
    -0.23
    ioc
    -0.22
    æ··åIJĪ
    -0.20
    è¡£
    -0.20
    enc
    -0.19
    .ix
    -0.18
     ming
    -0.18
    istar
    -0.18
     tern
    -0.18
     mixture
    -0.18
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.25
    ä¼ī
    0.20
     copp
    0.20
    çĽ¸å·®
    0.20
    sym
    0.20
    anko
    0.20
    缸èģļ
    0.20
     ******************************************************************************↵
    0.19
    suspend
    0.19
    å¦Ĵ
    0.19
    Activations Density 0.176%

    No Known Activations