© 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. 2271
    Prev
    Next
    INDEX
    Explanations

    specific words

    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
    ä¸Ģ次æĢ§
    -0.27
     Dash
    -0.23
    Pure
    -0.21
    å¤ĸåĩº
    -0.21
    çĶŁç´ł
    -0.21
    æIJ¬å®¶
    -0.21
    åįĪé¤IJ
    -0.21
    æ´¾éģ£
    -0.21
     Lunch
    -0.21
     Exact
    -0.21
    POSITIVE LOGITS
    æĬļæij¸
    0.33
    ç»Ĩèħ»
    0.32
    æĬļ
    0.29
    ä¸Ģéģį
    0.27
    toy
    0.26
    å®īæĬļ
    0.25
    oxel
    0.23
    -muted
    0.23
    curl
    0.23
     spine
    0.23
    Activations Density 0.009%

    No Known Activations