© 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. 11919
    Prev
    Next
    INDEX
    Explanations

    mini

    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
    inium
    -0.18
     اÙĦÙĨÙģ
    -0.18
    fully
    -0.18
    /ex
    -0.18
    -0.17
     Ñģобой
    -0.17
    .setSize
    -0.17
    æ®ĸ
    -0.17
    nable
    -0.16
    Tp
    -0.16
    POSITIVE LOGITS
    ãģĤãĤĬãģ¾ãģĻ
    0.20
    PLICATION
    0.20
    Remarks
    0.19
    å¤ļãģĦ
    0.17
    isable
    0.17
    ../../
    0.17
    ryan
    0.17
    Ä°L
    0.17
    ORIGINAL
    0.17
     damer
    0.17
    Activations Density 0.007%

    No Known Activations