© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2268
    Prev
    Next
    INDEX
    Explanations

    consecutive wins / eighth run / around 5 old

    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
    ä¸Ĭä¸ĭ游
    -0.22
     faculties
    -0.22
    åĽ°æī°
    -0.21
    ç¦Ħ
    -0.21
    ient
    -0.21
    æī«ä¸Ģæī«
    -0.21
     et
    -0.21
    åįĩ温
    -0.21
    å°±æľīäºĨ
    -0.21
    éĥ½ä¼ļæľī
    -0.20
    POSITIVE LOGITS
    æľĢå¤ļçļĦ
    0.24
     наи
    0.23
    çĦ¶æĺ¯
    0.22
    æİĴåIJį第ä¸Ģ
    0.22
    apiro
    0.22
     trailing
    0.22
    /on
    0.21
     theirs
    0.21
    ãģĹãĤĩãģĨ
    0.21
    essian
    0.21
    Activations Density 0.021%

    No Known Activations