© 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. 3081
    Prev
    Next
    INDEX
    Explanations

    property of

    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
    ildo
    -0.25
    ibt
    -0.24
    lut
    -0.24
    IOR
    -0.23
    ç»Īäºİ
    -0.22
    éĢĤæŶ
    -0.22
    åIJ¹
    -0.22
    Needed
    -0.21
    æªĶ
    -0.21
    lamp
    -0.21
    POSITIVE LOGITS
    ä¸į容
    0.28
    ä½ľèĢħæīĢæľī
    0.24
    åݳ
    0.24
     belongs
    0.24
     Corporation
    0.23
    屬
    0.23
     Az
    0.23
     ow
    0.23
     Almighty
    0.22
     whatsoever
    0.22
    Activations Density 0.005%

    No Known Activations