© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 660
    Prev
    Next
    INDEX
    Explanations

    unique, unusual, different

    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
    æĪĸåħ¶ä»ĸ
    -0.23
     Äijâu
    -0.23
    ÑģÑĤеÑĢ
    -0.22
    actable
    -0.22
    iful
    -0.22
     louder
    -0.22
    æĹ©æĹ¥
    -0.22
    ounce
    -0.22
     sooner
    -0.22
     вÑģÑı
    -0.21
    POSITIVE LOGITS
     unique
    0.60
    çĭ¬çī¹çļĦ
    0.56
    çĭ¬çī¹
    0.55
    unique
    0.54
    çī¹æ®ĬçļĦ
    0.53
     unusual
    0.52
    (unique
    0.51
     unconventional
    0.49
    Unique
    0.49
    .unique
    0.47
    Activations Density 0.173%

    No Known Activations