© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 482
    Prev
    Next
    INDEX
    Explanations

    words ending in -al, -ical, -ological

    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
    ings
    -0.31
    lessness
    -0.29
    entially
    -0.26
    çľ¼è§Ĵ
    -0.26
    ÂŃing
    -0.25
    estar
    -0.25
    linger
    -0.25
    åĴĮæĶ¯æĮģ
    -0.24
    çľ¼è¢ĭ
    -0.24
    wards
    -0.24
    POSITIVE LOGITS
    ity
    0.45
    ITY
    0.42
    ité
    0.35
    ities
    0.34
    ized
    0.33
    mente
    0.33
    ität
    0.31
    iteit
    0.31
    itÃł
    0.29
     prowess
    0.29
    Activations Density 1.640%

    No Known Activations