© 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. 1488
    Prev
    Next
    INDEX
    Explanations

    to no avail or limited effect

    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
    tight
    -0.28
    åĪ°åºķ
    -0.25
    toList
    -0.24
    çľĭå¾ħ
    -0.24
    ä½ķå¿ħ
    -0.24
     prem
    -0.23
    沿çĿĢ
    -0.22
    æĿ¥åģļ
    -0.22
    Compact
    -0.22
     concepts
    -0.22
    POSITIVE LOGITS
     dismay
    0.37
    éģĹæĨ¾
    0.31
    æĥĬ讶
    0.28
     surprise
    0.28
     detriment
    0.28
    ä¸įå°ı
    0.27
     surprisingly
    0.27
    æĥĭ
    0.27
    æĦıæĥ³ä¸įåĪ°
    0.27
     surpr
    0.27
    Activations Density 0.031%

    No Known Activations