© 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. 14637
    Prev
    Next
    INDEX
    Explanations

    market research reports

    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
    çģ«çĥ§
    -0.22
    lica
    -0.20
     عÙħ
    -0.19
    akis
    -0.19
    lip
    -0.18
    è´·
    -0.18
    '||
    -0.18
    ç»ĵå®ŀ
    -0.18
    ãĥıãĤ¦
    -0.18
     Fusion
    -0.17
    POSITIVE LOGITS
    æİ¥åĪ°
    0.20
    两年åīį
    0.19
    ä¸Ģä½į
    0.19
    PK
    0.19
    å¸Ĥæ°ij
    0.19
    æİĪäºĪ
    0.18
     вÑĭгод
    0.18
    toupper
    0.18
    è¿Ļå¥Ĺ
    0.18
    iani
    0.18
    Activations Density 0.003%

    No Known Activations