© 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. 1754
    Prev
    Next
    INDEX
    Explanations

    are typically

    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
    让å®ĥ
    -0.29
    éĩįæĸ°
    -0.27
    追踪
    -0.25
    (rename
    -0.25
    åĪ»
    -0.25
    åį³å°Ĩ
    -0.25
    çİĩè¾¾
    -0.24
    åį³å°ĨåĪ°æĿ¥
    -0.24
    æİĴéĻ¤
    -0.24
    æİ¥çĿĢ
    -0.24
    POSITIVE LOGITS
     notoriously
    0.41
     typically
    0.40
     inherently
    0.34
     generally
    0.34
     usually
    0.33
    éĢļ常
    0.32
    typically
    0.32
    çī¹æľīçļĦ
    0.32
    天çĶŁ
    0.31
     often
    0.31
    Activations Density 0.210%

    No Known Activations