© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12379
    Prev
    Next
    INDEX
    Explanations

    strollers, masturbator, TV box, holster, sealants

    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
    åįĬå¤ľ
    -0.21
    èģĴ
    -0.21
    è¿ĻçĤ¹
    -0.20
    aken
    -0.19
     case
    -0.19
    ServletContext
    -0.18
    spr
    -0.18
    andy
    -0.17
    proved
    -0.17
    æĢ¥äºİ
    -0.17
    POSITIVE LOGITS
    _pdata
    0.21
    å¼Ĥ
    0.20
    å¿ł
    0.19
    åħ¼åħ·
    0.19
    à¸Ĥà¸Ļา
    0.18
    羿
    0.18
     PaÅĦstwo
    0.18
     Fits
    0.18
     NORTH
    0.18
    _iso
    0.18
    Activations Density 0.388%

    No Known Activations