© 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. 15439
    Prev
    Next
    INDEX
    Explanations

    Louisville and names starting with Louis

    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
    nings
    -0.21
    geber
    -0.17
    alog
    -0.17
    ched
    -0.17
    ر
    -0.16
    èĽ¹
    -0.16
    omic
    -0.16
    forth
    -0.16
    ted
    -0.16
    aven
    -0.15
    POSITIVE LOGITS
    ï¸
    0.18
    -minded
    0.17
    ãĥĬãĤ¤
    0.15
    ened
    0.15
    iana
    0.15
    ðŁı»
    0.15
     NCAA
    0.14
    lad
    0.14
    ARD
    0.14
    ç¿©
    0.14
    Activations Density 0.008%

    No Known Activations