© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1739
    Prev
    Next
    INDEX
    Explanations

    song titles

    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
     Sofa
    -0.22
     SIN
    -0.22
     sofa
    -0.22
    %S
    -0.21
    çĩĥ
    -0.21
     Weekend
    -0.21
    çĥ
    -0.21
    (util
    -0.21
     QUICK
    -0.20
    æįŀ
    -0.20
    POSITIVE LOGITS
    åİĭå®ŀ
    0.28
    对åŃ©åŃIJ
    0.27
    onal
    0.25
    åħ¬è¯ģ
    0.23
    velt
    0.22
     Blo
    0.22
     IDisposable
    0.22
    igham
    0.21
    认
    0.21
     royal
    0.21
    Activations Density 0.001%

    No Known Activations