© 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. 350
    Prev
    Next
    INDEX
    Explanations

    obligated to, compelled to, necessary to

    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
    eyes
    -0.24
    襦
    -0.23
    è¹ĩ
    -0.23
    æĩĤå¾Ĺ
    -0.22
    æĥ³çĿĢ
    -0.22
    .imag
    -0.22
    rie
    -0.21
    éĵľ
    -0.21
    è¿IJ
    -0.21
     collar
    -0.20
    POSITIVE LOGITS
    è¡¥åħħ
    0.24
    å®īåħ¨æĦŁ
    0.23
    æľīå¿ħè¦ģ
    0.22
    请æķĻ
    0.22
    交å¾Ģ
    0.21
    å®īæħ°
    0.21
    è¡¥åģ¿
    0.21
     confess
    0.21
    é¢Ŀå¤ĸ
    0.21
    å±ıéļľ
    0.21
    Activations Density 0.007%

    No Known Activations