© 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. 13528
    Prev
    Next
    INDEX
    Explanations

    created by

    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
    /pub
    -0.22
    sing
    -0.19
    è¯Ŀ说
    -0.18
    idy
    -0.18
    EW
    -0.18
    _transition
    -0.18
    combe
    -0.18
    ações
    -0.18
    eos
    -0.18
    çĭ¨
    -0.18
    POSITIVE LOGITS
    สรร
    0.26
    åĪĿè¡·
    0.21
     created
    0.21
     קשר
    0.20
    created
    0.20
    -created
    0.20
     Created
    0.20
     conco
    0.20
    æ¦Ĥ念
    0.19
     Quar
    0.19
    Activations Density 0.077%

    No Known Activations