© 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. 1608
    Prev
    Next
    INDEX
    Explanations

    specifespecify_specific

    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
    mps
    -0.24
    æĮ¯ãĤĬ
    -0.24
    .ensure
    -0.23
    å³»
    -0.22
     stained
    -0.22
    reich
    -0.21
    åºŁå¼ĥçī©
    -0.21
    ìĨĶ
    -0.21
    论
    -0.21
    ä¹Ī
    -0.20
    POSITIVE LOGITS
    åħ·ä½ĵ
    0.35
    åħ·ä½ĵçļĦ
    0.34
    çļĦåħ·ä½ĵ
    0.32
     specifics
    0.31
    _specific
    0.31
    åħ·ä½ĵåĨħ容
    0.28
    specific
    0.27
    .timedelta
    0.27
    pee
    0.26
    TypeName
    0.26
    Activations Density 0.416%

    No Known Activations