© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 131
    Prev
    Next
    INDEX
    Explanations

    assigning blame or fault

    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
     interpol
    -0.26
     Bord
    -0.25
    æĹ¶æ®µ
    -0.25
    åIJ¦
    -0.24
    ä¸Ģåı£
    -0.23
    ÙĩÙĨ
    -0.23
     talks
    -0.23
    æ¸ħæ¥ļ
    -0.22
    æŀģ端
    -0.22
     licenses
    -0.22
    POSITIVE LOGITS
    åīįä¸ĸ
    0.24
    borne
    0.24
    VILLE
    0.23
    _MAJOR
    0.23
     Mets
    0.23
    èĢķèĢĺ
    0.22
     Heavenly
    0.22
     deserving
    0.22
     conscient
    0.21
    reck
    0.21
    Activations Density 0.006%

    No Known Activations