© 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. 1253
    Prev
    Next
    INDEX
    Explanations

    unexpected outcomes and negative states

    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
    çģµæķı
    -0.29
    æľīä¿¡å¿ĥ
    -0.28
    å·¡è§Ĩ
    -0.27
    è¶ĬæĿ¥è¶Ĭ好
    -0.26
    çĤ¹å¤´
    -0.26
    åı¯çĸij
    -0.24
    çĪ±ç¾İ
    -0.23
    .CommandType
    -0.23
    æļĤæŶ
    -0.23
    .Areas
    -0.23
    POSITIVE LOGITS
    åIJİæĤĶ
    0.40
     unexpectedly
    0.33
     unfore
    0.33
    æīįåıijçİ°
    0.32
     unexpected
    0.32
     realize
    0.32
    åħijçİ°
    0.29
    åIJİæľŁ
    0.28
     realizing
    0.28
    å¤±æľĽ
    0.28
    Activations Density 0.124%

    No Known Activations