© 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. 1871
    Prev
    Next
    INDEX
    Explanations

    names of people

    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
     Gareth
    -0.22
     meme
    -0.22
    UUID
    -0.21
     Fiona
    -0.21
    -
    -0.21
    IQ
    -0.20
    Ctrl
    -0.20
    Ele
    -0.20
    Qualified
    -0.20
    ï¸ı
    -0.20
    POSITIVE LOGITS
    ÑĩÑĢежден
    0.23
    é£ŀ
    0.23
     Brown
    0.23
     ÑĦоÑĢмиÑĢова
    0.23
     Sig
    0.22
     Green
    0.22
     Port
    0.22
     Gr
    0.22
    olley
    0.22
     Fort
    0.22
    Activations Density 0.063%

    No Known Activations