© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3103
    Prev
    Next
    INDEX
    Explanations

    Appellate court cases

    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
     Tud
    -0.23
    ç®Ģ称
    -0.22
    å°±åĮ»
    -0.22
     Claus
    -0.22
    ä¸ĩæĪ·
    -0.21
    ray
    -0.21
     Orig
    -0.20
     melod
    -0.20
    weis
    -0.20
    两åįĥ
    -0.20
    POSITIVE LOGITS
    ctime
    0.24
    _maker
    0.22
     INST
    0.21
    .inst
    0.20
    que
    0.20
     EITHER
    0.20
    _pri
    0.20
     quo
    0.20
    -www
    0.20
    gfx
    0.20
    Activations Density 0.015%

    No Known Activations