© 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. 3031
    Prev
    Next
    INDEX
    Explanations

    invention relates to

    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
    æľį
    -0.27
    Absolutely
    -0.25
    Dash
    -0.24
    æ´ŀ
    -0.24
    elo
    -0.24
     ping
    -0.24
    Reach
    -0.24
     tent
    -0.23
     retr
    -0.23
    tributes
    -0.23
    POSITIVE LOGITS
     foregoing
    0.32
    该æ¡Ī
    0.28
    æīĢè¿°
    0.27
    åīįè¿°
    0.26
    bose
    0.25
    ä¼ĺéĢī
    0.24
     notwithstanding
    0.24
    -described
    0.24
    åıijæĺİ
    0.24
     IHttp
    0.24
    Activations Density 0.094%

    No Known Activations