© 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. 1260
    Prev
    Next
    INDEX
    Explanations

    time durations or changes

    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
     invisible
    -0.27
    Trust
    -0.25
     Trusted
    -0.24
    åĩºèµĦ
    -0.24
     metadata
    -0.23
    ä¿¡ä»»
    -0.23
     trusted
    -0.23
    被åĪ¤
    -0.23
    æĦŁæĥħ
    -0.23
    æĬķ身
    -0.22
    POSITIVE LOGITS
    缩çŁŃ
    0.40
    ä½ľæģ¯
    0.37
    ç´§åĩij
    0.35
     Sundays
    0.34
    æĶ¹éĿ©
    0.33
     shorter
    0.32
    çļĦ好å¤Ħ
    0.31
    èĬĤåģĩæĹ¥
    0.31
     weekday
    0.31
    è°ĥæķ´
    0.31
    Activations Density 0.025%

    No Known Activations