© 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. 383
    Prev
    Next
    INDEX
    Explanations

    degrees and affiliations

    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
    sonian
    -0.26
    tober
    -0.24
    »¿
    -0.24
    foil
    -0.23
    UCCESS
    -0.22
    .partial
    -0.22
    ONSE
    -0.22
    _colour
    -0.22
    æĢ»å±Ģ
    -0.22
    éĻIJæľŁ
    -0.21
    POSITIVE LOGITS
     SQL
    0.26
    è§Ī
    0.26
     hybrid
    0.24
    angi
    0.23
    span
    0.23
     hybrids
    0.22
    ç¼ĺ
    0.22
    追寻
    0.22
    ['_
    0.22
    âĺľ
    0.21
    Activations Density 0.003%

    No Known Activations