© 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. 2365
    Prev
    Next
    INDEX
    Explanations

    terrorist threats

    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¿Ŀåħ»
    -0.30
     rebate
    -0.29
    竣工
    -0.27
    è¡¥åģ¿
    -0.25
    èĪĴæľį
    -0.25
     amort
    -0.25
     upkeep
    -0.24
    èĪĴéĢĤçļĦ
    -0.24
    ç¾İè§Ĥ
    -0.24
     Nutrition
    -0.24
    POSITIVE LOGITS
    å¨ģèĥģ
    0.49
    çĬ¯ç½ª
    0.44
    åį±å®³
    0.43
    ä½ľæ¡Ī
    0.40
    è¢Ńåĩ»
    0.40
     threats
    0.40
     terrorist
    0.38
    è¿Ŀæ³ķçĬ¯ç½ª
    0.38
    æĶ»åĩ»
    0.37
     threat
    0.37
    Activations Density 0.052%

    No Known Activations