© 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. 2416
    Prev
    Next
    INDEX
    Explanations

    "true" followed by specific nouns

    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
    enate
    -0.19
    нÑĥл
    -0.19
     unthinkable
    -0.19
    estr
    -0.19
    CurrentUser
    -0.18
    管å§Ķä¼ļ
    -0.18
    edImage
    -0.18
    OfType
    -0.18
    uez
    -0.17
    teenth
    -0.17
    POSITIVE LOGITS
    /false
    0.46
    fulness
    0.34
    zza
    0.26
    ä¸İåIJ¦
    0.26
    -ish
    0.26
    fully
    0.25
    zilla
    0.25
    istic
    0.24
    blood
    0.24
    keeping
    0.24
    Activations Density 0.077%

    No Known Activations