© 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. 977
    Prev
    Next
    INDEX
    Explanations

    mis followed by negative outcomes

    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
    etical
    -0.20
    anager
    -0.19
    rise
    -0.19
    ä¸Ģ个æĸ°çļĦ
    -0.19
    ®
    -0.18
    лев
    -0.18
    urally
    -0.18
    rst
    -0.18
    abis
    -0.18
    unlikely
    -0.17
    POSITIVE LOGITS
    ellaneous
    0.33
    fully
    0.25
    (es
    0.24
    /false
    0.24
    issippi
    0.23
    pped
    0.21
    nees
    0.21
    éĢĶ
    0.21
    ened
    0.21
    ä¹ĭå¤Ħ
    0.21
    Activations Density 0.029%

    No Known Activations