© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3055
    Prev
    Next
    INDEX
    Explanations

    untreated, not, or without

    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
    mma
    -0.23
     recognizes
    -0.23
    izza
    -0.23
     commend
    -0.23
     bloody
    -0.23
    èĩªå¦Ĥ
    -0.22
     recommend
    -0.22
    -sm
    -0.21
    ADV
    -0.21
     usefulness
    -0.20
    POSITIVE LOGITS
     unchecked
    0.34
    ä¸ĭåİ»
    0.32
    çĸı
    0.30
    _continue
    0.29
    太ä¹ħ
    0.28
    å¾Ĺä¸įåĪ°
    0.28
    继ç»Ń
    0.27
    ä¼ļ导èĩ´
    0.27
     improperly
    0.27
    继ç»Ńä¿ĿæĮģ
    0.27
    Activations Density 0.056%

    No Known Activations