© 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. 1258
    Prev
    Next
    INDEX
    Explanations

    prospects for the future

    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
    irth
    -0.19
    APS
    -0.19
    kö
    -0.19
    åī©
    -0.18
    -handed
    -0.18
    instant
    -0.17
    Processes
    -0.17
    ãģĹãģ¾ãģĨ
    -0.17
    thing
    -0.17
    ร
    -0.17
    POSITIVE LOGITS
    eur
    0.31
    ively
    0.31
    ivity
    0.27
    ion
    0.23
    acular
    0.23
    sWith
    0.23
    afil
    0.23
    ually
    0.22
    pective
    0.21
    si
    0.21
    Activations Density 0.020%

    No Known Activations