© 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. 13285
    Prev
    Next
    INDEX
    Explanations

    recession, recess, recessive

    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
    ãģijãĤĭ
    -0.20
    scheme
    -0.19
    ValuePair
    -0.19
     erect
    -0.18
    件äºĭ
    -0.17
    éĶ·
    -0.17
    -0.17
    subpackage
    -0.17
    å°Ķæĸ¯
    -0.17
    åľ¨å¤ĸéĿ¢
    -0.17
    POSITIVE LOGITS
    ary
    0.27
    naire
    0.23
    ible
    0.22
    -era
    0.21
    æľŁéĹ´
    0.21
    IGO
    0.19
    ally
    0.19
    éĻĽ
    0.18
    è¯Ŀ说
    0.18
    äºĨæĪijçļĦ
    0.18
    Activations Density 0.007%

    No Known Activations