© 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. 2897
    Prev
    Next
    INDEX
    Explanations

    ammunition and manpower

    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
    ramer
    -0.28
    abouts
    -0.25
    aways
    -0.23
    uate
    -0.23
    Advertisement
    -0.23
    inder
    -0.22
    ãĤĤãģ®
    -0.21
    inema
    -0.21
    åıįæŃ£
    -0.20
    Advertisements
    -0.20
    POSITIVE LOGITS
    é½IJåħ¨
    0.23
    åħħ足
    0.23
    åħħæ²Ľ
    0.22
    庫
    0.22
    wagon
    0.22
    jom
    0.21
    åŀĽ
    0.21
    erland
    0.20
    ëį°
    0.20
    åħħè£ķ
    0.20
    Activations Density 0.006%

    No Known Activations