© 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. 2472
    Prev
    Next
    INDEX
    Explanations

    place

    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
    fühl
    -0.22
    ä¸įåIJĥ
    -0.22
    coverage
    -0.21
    shuffle
    -0.21
     Continental
    -0.21
     recon
    -0.21
    çĺ¤
    -0.21
    å°½åı¯èĥ½
    -0.21
     Lub
    -0.21
    anken
    -0.21
    POSITIVE LOGITS
    ä½įäºİ
    0.38
     tucked
    0.36
     hidden
    0.35
     located
    0.35
    ä½įç½®
    0.35
    éļIJèĶ½
    0.34
     accessible
    0.33
    çļĦä½įç½®
    0.33
    æīĢåľ¨
    0.33
    éļIJèĹı
    0.33
    Activations Density 0.132%

    No Known Activations