© 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. 396
    Prev
    Next
    INDEX
    Explanations

    seminar or seminars

    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
    ermen
    -0.24
    åij¸
    -0.19
    lessly
    -0.19
     canonical
    -0.19
     Meer
    -0.19
     зÑĢ
    -0.19
    sen
    -0.19
    idious
    -0.18
    ention
    -0.18
    ively
    -0.18
    POSITIVE LOGITS
    igan
    0.22
     vitae
    0.22
    awe
    0.21
    #{
    0.20
    /pr
    0.20
     dotyczÄħ
    0.20
    éŨåı£
    0.19
     halls
    0.19
     Bahamas
    0.19
    лÑİд
    0.19
    Activations Density 0.005%

    No Known Activations