© 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. 14008
    Prev
    Next
    INDEX
    Explanations

    ensuing or resulting

    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
    ity
    -0.19
    át
    -0.18
    éªĿ
    -0.18
    tea
    -0.18
    izations
    -0.18
    橹
    -0.17
    绣é¢Ĩ
    -0.17
    ãĤĥ
    -0.17
    说åĪ°è¿ĻéĩĮ
    -0.17
    _usage
    -0.16
    POSITIVE LOGITS
    ed
    0.24
    æĦŁæ¿Ģ
    0.18
     Grat
    0.18
     ----------------------------------------------------------------------------------------------------------------
    0.17
    eed
    0.17
    æłĩéħį
    0.16
    .locals
    0.16
    åķĨæľº
    0.15
     дела
    0.15
    wald
    0.15
    Activations Density 0.003%

    No Known Activations