© 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. 3130
    Prev
    Next
    INDEX
    Explanations

    send or receive email

    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
    алÑĮн
    -0.26
    æıŃ
    -0.23
    çĻ¾åĪĨ
    -0.23
    å¸ĥå±Ģ
    -0.23
    émon
    -0.23
    ç¦ıçĶ°
    -0.22
     yourselves
    -0.22
    åIJ¦å®ļ
    -0.21
    ä¸Ģåı£
    -0.21
    ientes
    -0.21
    POSITIVE LOGITS
    çĨĦ
    0.27
     Licence
    0.24
     offending
    0.23
    èĦ±åıij
    0.22
    åĺī宾
    0.22
     licences
    0.22
     halluc
    0.22
    çĵ¢
    0.22
    éģĩåĪ°
    0.21
     licence
    0.21
    Activations Density 0.002%

    No Known Activations