© 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. 230
    Prev
    Next
    INDEX
    Explanations

    published edition

    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
    idon
    -0.23
    ONO
    -0.23
    deo
    -0.23
    ðŁı»
    -0.21
    EVER
    -0.20
    Ī
    -0.19
    letal
    -0.19
    ingly
    -0.19
    INGS
    -0.19
     assorted
    -0.18
    POSITIVE LOGITS
    airy
    0.21
    wise
    0.21
    ll
    0.21
    -wise
    0.21
    naire
    0.21
    iste
    0.20
    ми
    0.20
    /rem
    0.20
    /new
    0.20
    ively
    0.20
    Activations Density 0.009%

    No Known Activations