© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 978
    Prev
    Next
    INDEX
    Explanations

    ideal, ideally, preferable

    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
    edata
    -0.23
    çī¹çĤ¹æĺ¯
    -0.22
     milestone
    -0.22
    ÑģÑı
    -0.22
    æľº
    -0.22
    å¿ħãģļ
    -0.22
    downloads
    -0.21
    æľĢéĩįè¦ģçļĦ
    -0.21
     meticulous
    -0.21
     Firm
    -0.21
    POSITIVE LOGITS
     ideal
    0.31
    åı¯æĥľ
    0.30
    çIJĨæĥ³
    0.30
    æĦ¿æľĽ
    0.29
     ideally
    0.28
     Ideal
    0.28
    çļĦçIJĨæĥ³
    0.27
     preferable
    0.27
    æģIJæĢķ
    0.26
    ideal
    0.26
    Activations Density 0.075%

    No Known Activations