© 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. 832
    Prev
    Next
    INDEX
    Explanations

    flood, avalanche, torrent, deluge

    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
     minimal
    -0.24
    lessness
    -0.23
    hood
    -0.23
     grado
    -0.22
    éļĻ
    -0.21
    minimal
    -0.21
    мÑĥ
    -0.21
    ç¥Ĺ
    -0.21
    æľ
    -0.20
    å®ļåIJij
    -0.20
    POSITIVE LOGITS
    æ¶Įåħ¥
    0.46
    æ¶Įçİ°
    0.34
     onslaught
    0.33
    æ¶Įçİ°åĩº
    0.31
    æ¶Į
    0.29
    æ±¹
    0.29
    åIJĦå¼ıåIJĦæł·
    0.27
    浪潮
    0.27
     barrage
    0.27
    pour
    0.26
    Activations Density 0.039%

    No Known Activations