© 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. 2570
    Prev
    Next
    INDEX
    Explanations

    power and compound words

    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
    AMES
    -0.20
    ĵ
    -0.19
    ãĤĤãģ®
    -0.18
    udes
    -0.18
    opard
    -0.18
    yı
    -0.18
    verting
    -0.18
    ipping
    -0.17
    CriticalSection
    -0.17
    ogo
    -0.17
    POSITIVE LOGITS
    fully
    0.39
    houses
    0.29
    ful
    0.29
    lessness
    0.25
    oft
    0.24
    headed
    0.22
    çĪ·
    0.22
    lifting
    0.21
     mẽ
    0.20
    desk
    0.20
    Activations Density 0.068%

    No Known Activations