© 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. 2191
    Prev
    Next
    INDEX
    Explanations

    stewardship, safeguards, ship

    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
     trùng
    -0.23
    UnitOfWork
    -0.21
     gang
    -0.20
    voor
    -0.20
    çĺ¦èº«
    -0.20
    åĶ¬
    -0.19
    WWW
    -0.19
    ço
    -0.19
    asso
    -0.18
    ç½IJ
    -0.18
    POSITIVE LOGITS
    ship
    0.34
    ä¿Ŀåħ»
    0.25
    æľŁåĨħ
    0.25
    eer
    0.24
    keepers
    0.23
    /control
    0.23
    hip
    0.23
    bere
    0.23
    elves
    0.23
    èĩªçĦ¶èµĦæºIJ
    0.23
    Activations Density 0.003%

    No Known Activations