© 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. 298
    Prev
    Next
    INDEX
    Explanations

    fitness professionals or industry

    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
    edException
    -0.28
    sWith
    -0.27
    UMENT
    -0.23
    abouts
    -0.22
     chuyá»ĩn
    -0.22
    uments
    -0.22
    thern
    -0.22
    affle
    -0.20
    edList
    -0.20
    èĤļåŃIJ
    -0.19
    POSITIVE LOGITS
    s
    0.28
    es
    0.26
    -oriented
    0.24
    çĬ¶åĨµ
    0.22
    cope
    0.22
    -related
    0.22
    -minded
    0.22
    åī¯æł¡éķ¿
    0.21
    l
    0.21
    -seeking
    0.20
    Activations Density 0.006%

    No Known Activations