© 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. 1465
    Prev
    Next
    INDEX
    Explanations

    followed by

    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
    -mean
    -0.25
    è¿Ļæĺ¯åĽłä¸º
    -0.23
    è¿ĻçĤ¹
    -0.23
    è¿Ļä¸ĢçĤ¹
    -0.23
    loh
    -0.23
    ierge
    -0.22
    ills
    -0.21
    -minded
    -0.21
     themselves
    -0.21
    åºķ
    -0.20
    POSITIVE LOGITS
    ä¸Ģç³»åĪĹ
    0.29
    缸åºĶçļĦ
    0.27
     optionally
    0.25
    äºĨä¸Ģç³»åĪĹ
    0.25
    edBy
    0.25
     Optionally
    0.25
     corresponding
    0.25
    ç´§æİ¥çĿĢ
    0.24
    åĩłåı¥
    0.24
    hin
    0.24
    Activations Density 0.030%

    No Known Activations