© 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. 3350
    Prev
    Next
    INDEX
    Explanations

    rooms and facilities

    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
    Negative Logits
    åĭŁ
    -0.26
     Tatto
    -0.25
    å¤§åľ°
    -0.24
    éĶŃ
    -0.23
     Casinos
    -0.23
     Mild
    -0.22
    å±Ĥå±Ĥ
    -0.22
     Bras
    -0.22
     voted
    -0.21
    lige
    -0.21
    POSITIVE LOGITS
     mini
    0.30
    mini
    0.30
     miniature
    0.28
    客åİħ
    0.26
     полно
    0.26
    rost
    0.25
    åľ¨éĩĮéĿ¢
    0.25
     posing
    0.24
    家ä¸Ń
    0.24
     access
    0.24
    Activations Density 0.011%

    No Known Activations