© 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. 1367
    Prev
    Next
    INDEX
    Explanations

    days of week followed by dates/times

    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
    åħ»æĪIJ
    -0.24
    ä¹ĭéĻħ
    -0.24
    éĤij
    -0.23
    /rem
    -0.23
     UPS
    -0.23
    寿
    -0.22
    æĸ°æĹ¶æľŁ
    -0.22
    å®ļæľŁ
    -0.22
    çĶµè¯Ŀ
    -0.22
    å®ŀè´¨æĢ§
    -0.22
    POSITIVE LOGITS
    ALLOC
    0.28
     breakout
    0.28
     bölüm
    0.26
    åĺī宾
    0.26
     chaired
    0.25
    _AVAILABLE
    0.25
     during
    0.24
    atings
    0.24
     keynote
    0.24
    è§Ĥä¼Ĺ
    0.24
    Activations Density 0.051%

    No Known Activations