© 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. 1224
    Prev
    Next
    INDEX
    Explanations

    pro se

    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
     VIN
    -0.24
    åı³ä¾§
    -0.23
    VIN
    -0.23
    æĬĢå¸Ī
    -0.23
    以éĺ²
    -0.23
    çĽĹ
    -0.23
     maintenance
    -0.21
    对ä¸įèµ·
    -0.21
     private
    -0.21
     Dut
    -0.20
    POSITIVE LOGITS
    emplate
    0.24
    å±ķé¦Ĩ
    0.24
     Honest
    0.23
    æ£Ĥ
    0.23
    æī©æķ£
    0.23
     Rhe
    0.22
    _behavior
    0.22
     lenses
    0.22
    _transition
    0.21
     [](
    0.21
    Activations Density 0.004%

    No Known Activations