© 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. 3064
    Prev
    Next
    INDEX
    Explanations

    schedule hearing or develop documents

    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
    èįŀ
    -0.24
     mortal
    -0.23
     cyn
    -0.23
    DISABLE
    -0.23
     confessed
    -0.22
    stitial
    -0.22
    stral
    -0.22
    ä¸įåľ¨ä¹İ
    -0.22
     DISABLE
    -0.22
    Pairs
    -0.22
    POSITIVE LOGITS
    ä¸ºä½ł
    0.30
     forwarding
    0.26
    æ¡Įä¸Ĭ
    0.26
    为æĤ¨
    0.26
     internally
    0.25
    /internal
    0.23
    å¸®ä½ł
    0.23
    æŁ¥æī¾
    0.22
     overnight
    0.22
     specialists
    0.22
    Activations Density 0.022%

    No Known Activations