© 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. 2027
    Prev
    Next
    INDEX
    Explanations

    fact that

    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
    ä¸įä½Ĩ
    -0.27
    either
    -0.25
    ä¸įä»ħ
    -0.24
     Ah
    -0.23
     either
    -0.23
     kut
    -0.23
    éĢļè¿ĩ对
    -0.23
    å¦Ĥæŀľä¸į
    -0.23
    åıªè¦ģ
    -0.23
    fv
    -0.23
    POSITIVE LOGITS
    è¿Ļä¸ĢçĤ¹
    0.31
     fact
    0.27
    è¿ĻçĤ¹
    0.27
    endale
    0.25
     ÑĦакÑĤ
    0.24
    è¿Ļä¹Īå¤ļ
    0.24
    å¤ĸåªĴ
    0.23
     (!_
    0.23
    èĪģ
    0.23
     lẫn
    0.23
    Activations Density 0.027%

    No Known Activations