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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 351
    Prev
    Next
    INDEX
    Explanations

    La followed by specific 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
    nya
    -0.30
    nia
    -0.25
    ra
    -0.24
    ll
    -0.24
    szed
    -0.22
    tures
    -0.22
    ÑĤин
    -0.22
    padÅĤ
    -0.22
    lah
    -0.21
    noc
    -0.21
    POSITIVE LOGITS
    ž
    0.24
    ceed
    0.23
    ffect
    0.22
    -même
    0.22
    uess
    0.22
    urent
    0.22
    ves
    0.22
    ï¬Ģ
    0.21
    -dess
    0.21
    amp
    0.21
    Activations Density 0.077%

    No Known Activations