© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 5
    Prev
    Next
    INDEX
    Explanations

    taste and aesthetics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
     breakout
    -0.23
    /single
    -0.21
     Möglichkeit
    -0.21
    å¸Ń
    -0.21
    asca
    -0.21
    LTE
    -0.21
    (AT
    -0.20
    åįĥåı¤
    -0.20
     padd
    -0.20
     Svens
    -0.20
    POSITIVE LOGITS
    审ç¾İ
    0.35
     taste
    0.30
    æķıéĶIJ
    0.29
    åĪ¤æĸŃ
    0.27
     aesthetics
    0.26
     cultivated
    0.26
     cultured
    0.26
    æĮijåīĶ
    0.25
     instincts
    0.25
    ä¿®åħ»
    0.25
    Activations Density 0.022%

    No Known Activations