© 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. 14655
    Prev
    Next
    INDEX
    Explanations

    charity: water, dinner, album, work

    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
    èĢģå®ŀ
    -0.19
    ä¸įåłª
    -0.17
    stakes
    -0.17
    ritten
    -0.17
    perience
    -0.16
    edor
    -0.16
    ÑĩаÑĤ
    -0.16
    .hostname
    -0.16
    ival
    -0.16
    imum
    -0.16
    POSITIVE LOGITS
    opsy
    0.20
    éĺĹ
    0.19
    istic
    0.19
    yyy
    0.17
    è¡·
    0.16
    -minded
    0.16
    ific
    0.16
     corrid
    0.15
    anded
    0.15
    ware
    0.15
    Activations Density 0.006%

    No Known Activations