© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2331
    Prev
    Next
    INDEX
    Explanations

    preposition followed by definite article

    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
    èĩ³
    -0.23
    i
    -0.22
    ä¹ĭ
    -0.21
    redi
    -0.20
    itud
    -0.20
    çļĦèĢģ
    -0.20
    ahl
    -0.20
    çļĦ
    -0.20
    f
    -0.20
    ãģ«åIJijãģijãģ¦
    -0.19
    POSITIVE LOGITS
    /lic
    0.25
    å·²ä¹ħçļĦ
    0.23
    å·²ä¹ħ
    0.23
    abox
    0.22
    {lng
    0.22
    /cop
    0.21
    \">↵
    0.21
    /off
    0.21
     mükem
    0.21
    theid
    0.20
    Activations Density 0.469%

    No Known Activations