© 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. 969
    Prev
    Next
    INDEX
    Explanations

    plans and services

    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
    ç»ĦåĽ¾
    -0.24
     act
    -0.23
     grouping
    -0.23
     phase
    -0.23
    个åĪ«
    -0.22
    éĹ´è·Ŀ
    -0.22
    lay
    -0.22
    QUIRED
    -0.22
    nels
    -0.22
    åĪĨåĪ«ä¸º
    -0.22
    POSITIVE LOGITS
    .daily
    0.28
     plum
    0.24
     churn
    0.24
    éļıæŶéļıåľ°
    0.24
    çĶļèĩ³è¿ĺ
    0.23
    exc
    0.23
     subscription
    0.23
     доÑģÑĤÑĥп
    0.23
    å´Ń
    0.23
     subscribers
    0.22
    Activations Density 0.002%

    No Known Activations