© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17224
    Prev
    Next
    INDEX
    Explanations

    raising funds, awareness, or donations

    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
    Negative Logits
    ´
    -0.21
    ually
    -0.20
    ting
    -0.18
    æ°ijå¿ĥ
    -0.18
    jur
    -0.17
    iques
    -0.17
    车ä¸Ĭ
    -0.16
    æ·±å¤Ħ
    -0.16
    swer
    -0.16
    raries
    -0.16
    POSITIVE LOGITS
    èѦæĥķ
    0.29
     havoc
    0.22
    ðŁı»
    0.21
    åĴĮå®ĮåĸĦ
    0.20
    /de
    0.19
     eyebrows
    0.18
    çĸijéĹ®
    0.17
    å¾Īé«ĺçļĦ
    0.17
    çľ¼çķĮ
    0.17
    ãĤĤãģĨ
    0.17
    Activations Density 0.026%

    No Known Activations