© 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. 1
    Prev
    Next
    INDEX
    Explanations

    between something

    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
    Ñıз
    -0.22
    inal
    -0.22
    ual
    -0.21
    ORK
    -0.21
    UAL
    -0.21
    bearer
    -0.21
    module
    -0.20
    roma
    -0.20
     Mutual
    -0.20
     detriment
    -0.19
    POSITIVE LOGITS
    æŃĩ
    0.28
    å¿ĻçĿĢ
    0.25
    æľīæķĪæľŁ
    0.24
     ÙĪبÙĬÙĨ
    0.23
     between
    0.23
    æ¿ĢçĥĪçļĦ
    0.23
    ely
    0.22
    _phrase
    0.22
    ç¢İ
    0.22
     Isles
    0.22
    Activations Density 0.048%

    No Known Activations