© 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. 1030
    Prev
    Next
    INDEX
    Explanations

    your/their feedback/support/contributions

    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
    eno
    -0.26
    èĩªåįij
    -0.24
     Trilogy
    -0.22
    说ä¸įåĩº
    -0.21
    å®ŀçİ°äºĨ
    -0.21
    reno
    -0.21
    實çı¾
    -0.21
    @js
    -0.20
    quit
    -0.20
     Circus
    -0.20
    POSITIVE LOGITS
    建议
    0.28
    åģķ
    0.25
    ä½łä»¬
    0.24
    åı¯ä»¥å¸®åĬ©
    0.24
     catalogs
    0.24
     suggestions
    0.23
    ãģľãģ²
    0.23
     urgently
    0.23
     please
    0.23
    æ¶ī
    0.23
    Activations Density 0.046%

    No Known Activations