© 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. 3120
    Prev
    Next
    INDEX
    Explanations

    current or latest information

    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
    åīįéĢĶ
    -0.25
    oins
    -0.25
    .ru
    -0.22
    acon
    -0.22
    (Component
    -0.22
    oti
    -0.21
     arte
    -0.21
    ITS
    -0.21
    aal
    -0.21
    亲çĪ±
    -0.21
    POSITIVE LOGITS
    /current
    0.31
    /latest
    0.26
     edition
    0.24
     incarnation
    0.24
     available
    0.24
    OrDefault
    0.24
     cached
    0.23
     Updated
    0.23
     акÑĤÑĥ
    0.22
    born
    0.22
    Activations Density 0.013%

    No Known Activations