© 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. 16518
    Prev
    Next
    INDEX
    Explanations

    able or editable

    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
    ing
    -0.25
    ed
    -0.24
    ical
    -0.23
    ers
    -0.23
    el
    -0.21
    edBy
    -0.21
    uite
    -0.20
    ese
    -0.20
    ological
    -0.20
    ern
    -0.19
    POSITIVE LOGITS
    -bodied
    0.25
    ä¹ĭå¤Ħ
    0.23
    ITY
    0.21
    tics
    0.20
    keiten
    0.20
    keit
    0.20
    -minded
    0.19
    mente
    0.19
     minded
    0.18
    NESS
    0.18
    Activations Density 0.186%

    No Known Activations