© 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. 2359
    Prev
    Next
    INDEX
    Explanations

    importantly and all

    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
    æŃ£å¥½
    -0.28
    oret
    -0.26
     similarly
    -0.26
    å°±å¾Ī
    -0.25
     supposedly
    -0.25
     вполне
    -0.25
     necessarily
    -0.25
     alternatively
    -0.25
    æŁIJç§įç¨ĭ度
    -0.24
     zwar
    -0.24
    POSITIVE LOGITS
    èİ«è¿ĩäºİ
    0.30
    æľĢéĩįè¦ģ
    0.28
    æľĢéĩįè¦ģçļĦ
    0.28
     HUGE
    0.26
    æľĢåħ³éĶ®
    0.25
    Fear
    0.25
    å¸ĮæľĽå¤§å®¶
    0.25
     ниÑĩего
    0.24
     NOTHING
    0.24
    æľĢåŁºæľ¬
    0.24
    Activations Density 0.053%

    No Known Activations