© 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. 1032
    Prev
    Next
    INDEX
    Explanations

    no longer

    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¸Ģèīĺ
    -0.24
    æĸ¹æīį
    -0.23
    ä¸Ģ件
    -0.22
    ableView
    -0.22
    Evaluation
    -0.22
    å¿ĥè·³
    -0.22
    æ±ľ
    -0.22
     Bearings
    -0.21
    ä¸Ģé¢Ĺ
    -0.21
    岫
    -0.21
    POSITIVE LOGITS
     legacy
    0.41
    æŧ
    0.39
     old
    0.35
    åİŁæľīçļĦ
    0.35
    èĢģæŧ
    0.35
     traditional
    0.34
    ä¼łç»ŁçļĦ
    0.33
    èĪĬ
    0.32
     Legacy
    0.32
    	old
    0.32
    Activations Density 0.133%

    No Known Activations