© 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. 2752
    Prev
    Next
    INDEX
    Explanations

    by and Reviewed

    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
    eneg
    -0.24
     reinforcements
    -0.22
    (factory
    -0.22
     bell
    -0.21
    gregate
    -0.21
     systematically
    -0.21
     wink
    -0.21
    >{@
    -0.21
    Hierarchy
    -0.21
    æĶ¾å®½
    -0.20
    POSITIVE LOGITS
    çĶŁäº§ç»ıèIJ¥
    0.26
     âĺħ
    0.24
     Pron
    0.24
    Guard
    0.23
    éĩĬ
    0.23
    Reviewed
    0.23
    Released
    0.23
     Reviewed
    0.23
    éĹ®è¯¢
    0.23
    guard
    0.23
    Activations Density 0.089%

    No Known Activations