© 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. 946
    Prev
    Next
    INDEX
    Explanations

    going crazy or insane

    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
    éĽĦ
    -0.26
    å¾Ī强
    -0.25
     slips
    -0.24
    æ·±åĪĩ
    -0.24
     slip
    -0.24
    å¾Īé«ĺ
    -0.24
    å³¥
    -0.24
     closely
    -0.23
     spre
    -0.22
     Gerry
    -0.22
    POSITIVE LOGITS
    ingly
    0.25
    æĤ¬å¿µ
    0.24
    preserve
    0.24
    çľĭå®Į
    0.24
    alive
    0.24
    åıĹä¸įäºĨ
    0.24
    ()._
    0.23
    åīįä¸Ģ天
    0.23
    åħ¶éĹ´
    0.22
    ease
    0.22
    Activations Density 0.023%

    No Known Activations