© 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. 14489
    Prev
    Next
    INDEX
    Explanations

    hatch and latch

    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
     Ñģобой
    -0.19
    ТЬ
    -0.17
    _cast
    -0.16
    atics
    -0.15
    tran
    -0.15
    PLEX
    -0.15
     Elk
    -0.15
    _markers
    -0.15
    ikut
    -0.15
    icamente
    -0.15
    POSITIVE LOGITS
    ling
    0.21
    lings
    0.20
    imonial
    0.19
    lew
    0.17
    ãĤĤãģ®
    0.17
    ett
    0.17
    çİĩ
    0.17
    lam
    0.16
    åŃIJéĩĮ
    0.16
    è±Į
    0.16
    Activations Density 0.005%

    No Known Activations