© 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. 1369
    Prev
    Next
    INDEX
    Explanations

    free offers and prizes

    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
    lichkeit
    -0.25
    èĢģé¾ĦåĮĸ
    -0.24
    arnation
    -0.24
    borough
    -0.24
    tabpanel
    -0.23
    ialect
    -0.23
    以人为
    -0.23
    atism
    -0.22
    [...,
    -0.22
    erah
    -0.22
    POSITIVE LOGITS
     gratis
    0.28
     kit
    0.27
    å°Ĩä¼ļ
    0.25
     coupon
    0.25
     coupons
    0.24
    icorn
    0.24
     consolation
    0.24
     ÙħجاÙĨÙĬ
    0.24
    å¯¹ä½ł
    0.24
    åħįè´¹
    0.24
    Activations Density 0.049%

    No Known Activations