© 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. 635
    Prev
    Next
    INDEX
    Explanations

    national team appearances

    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
     incomplete
    -0.25
     obstruct
    -0.24
     Firm
    -0.23
     initData
    -0.22
     firm
    -0.22
    ä¸įæ¸ħ
    -0.21
     false
    -0.21
    é¾Ļ
    -0.21
     incorrect
    -0.21
    åIJ«æľī
    -0.21
    POSITIVE LOGITS
    åı£å¾Ħ
    0.31
    åĽ½å®¶éĺŁ
    0.27
    /world
    0.26
     Batter
    0.25
    -worthy
    0.25
    -team
    0.24
    éĿĴå¹´
    0.24
    å¤ĩæĪĺ
    0.24
     batter
    0.23
    ering
    0.23
    Activations Density 0.022%

    No Known Activations