© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 223
    Prev
    Next
    INDEX
    Explanations

    . followed by capital letter

    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
    (...)
    -0.26
     \$
    -0.26
     г
    -0.24
     (...)
    -0.24
     magazine
    -0.24
    ()}
    -0.24
     Academy
    -0.24
     video
    -0.24
     warm
    -0.23
     t
    -0.23
    POSITIVE LOGITS
    åħ¶å®ĥéĹ®é¢ĺ
    0.30
    è¹¼
    0.30
     similarly
    0.29
    iaux
    0.29
    类似
    0.28
    similar
    0.27
    ä¸ĢèĪ¬äºº
    0.26
    è¿ĶåĽŀæIJľçĭIJ
    0.25
    éĢ²ä¸ĢæŃ¥
    0.25
    å°Ĩè¿Ľä¸ĢæŃ¥
    0.25
    Activations Density 0.698%

    No Known Activations