© 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. 1398
    Prev
    Next
    INDEX
    Explanations

    had been

    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
     Dit
    -0.24
    å°Ĩ继ç»Ń
    -0.22
    mens
    -0.22
    magic
    -0.21
    åī¯æĢ»
    -0.21
    nds
    -0.21
    ä¾ij
    -0.21
    _mC
    -0.20
    æĢªçī©
    -0.20
    èĢģ头
    -0.20
    POSITIVE LOGITS
     earlier
    0.39
     ÑĢанее
    0.35
     previously
    0.35
     previous
    0.34
    ä¹ĭåīį
    0.33
     preceding
    0.33
    åħĪåīį
    0.32
    åľ¨æѤä¹ĭåīį
    0.29
     wczeÅĽniej
    0.28
     beforehand
    0.28
    Activations Density 0.115%

    No Known Activations