© 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. 2668
    Prev
    Next
    INDEX
    Explanations

    contractions like don't, haven't, didn't

    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
     replicate
    -0.24
    anked
    -0.23
    迸
    -0.23
    lung
    -0.22
    lux
    -0.22
    çĬĢ
    -0.22
    èĪĤ
    -0.21
    åĽłåľ°
    -0.21
     numeral
    -0.21
     replicated
    -0.21
    POSITIVE LOGITS
    æĪij们åºĶ该
    0.33
    æĪij认为
    0.32
    æĪij们å¿ħé¡»
    0.31
    æĪij们éľĢè¦ģ
    0.31
     hopefully
    0.28
    çİ°éĺ¶æ®µ
    0.28
    æĪij们è¦ģ
    0.28
    æīĴ
    0.27
    å¦ĤæŀľæĪij们
    0.26
     crappy
    0.25
    Activations Density 0.108%

    No Known Activations