© 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. 522
    Prev
    Next
    INDEX
    Explanations

    unsafe web content and files

    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
     plural
    -0.26
    æľīåĬĽ
    -0.25
    ä¼ĺåĬ¿
    -0.25
    çģµæ´»
    -0.25
    çģµæ´»æĢ§
    -0.24
    Gap
    -0.24
    åĽłåľ°åĪ¶å®ľ
    -0.24
    çļĦä¼ĺåĬ¿
    -0.24
    إدار
    -0.23
     Gap
    -0.23
    POSITIVE LOGITS
    çĤ¹åĩ»
    0.32
     harmless
    0.28
     unknow
    0.28
    身亡
    0.26
     decrypt
    0.26
     click
    0.26
    Unsafe
    0.26
    _clicked
    0.26
     innoc
    0.25
     clicked
    0.25
    Activations Density 0.016%

    No Known Activations