© 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. 11265
    Prev
    Next
    INDEX
    Explanations

    chiropractic adjustment joint medicine

    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
    _construct
    -0.23
    åĵģç§į
    -0.23
    èµ·çĤ¹
    -0.23
    管家
    -0.21
    æµĩ
    -0.21
    åĢ¨
    -0.21
    æµļ
    -0.20
    ground
    -0.20
    å¾Ģåīį
    -0.19
    ç»ĺçĶ»
    -0.19
    POSITIVE LOGITS
     chiropr
    0.25
    æīĭæ³ķ
    0.18
     IPAddress
    0.18
    éĵ¯
    0.18
    iropr
    0.18
     oz
    0.18
    å°ıçĻ½
    0.18
     CDs
    0.17
     pitch
    0.17
    æ¸ħ
    0.17
    Activations Density 0.014%

    No Known Activations