© 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. 1830
    Prev
    Next
    INDEX
    Explanations

    y followed by specific words

    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
    æĦıæĦ¿
    -0.21
    ials
    -0.21
    yntax
    -0.19
    OrUpdate
    -0.19
     entirety
    -0.19
     yếu
    -0.18
    转载
    -0.18
    çĪ·
    -0.18
     avenues
    -0.18
     realism
    -0.18
    POSITIVE LOGITS
    annis
    0.32
    ields
    0.30
    0.29
    osemite
    0.24
    psilon
    0.22
    vette
    0.22
    andex
    0.22
    esterday
    0.21
    'all
    0.21
    asmine
    0.21
    Activations Density 0.218%

    No Known Activations