© 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. 1205
    Prev
    Next
    INDEX
    Explanations

    making up for losses

    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
    æī¹è¯Ħ
    -0.23
    ä¹Łä¸įéĶĻ
    -0.23
    å±İ
    -0.22
    à¹Ģà¸Ĺศ
    -0.22
    渣
    -0.21
    sville
    -0.21
    ert
    -0.21
    èĢ³è¾¹
    -0.21
     Spo
    -0.21
    å¹²èĦĨ
    -0.21
    POSITIVE LOGITS
    è¡¥åģ¿
    0.33
    弥补
    0.30
     compensate
    0.28
    /mit
    0.27
    ÑĢож
    0.26
    upa
    0.25
    ulative
    0.25
    æĪIJé¾Ļ
    0.25
     compens
    0.24
    ç½ħ
    0.23
    Activations Density 0.007%

    No Known Activations