© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63540
    Prev
    Next
    INDEX
    Explanations

    relationship satisfaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    çĭĤ
    -0.10
    ÑĤиÑĢ
    -0.10
    idia
    -0.09
    ë¹Ļ
    -0.09
     shaved
    -0.09
    åĩºåħ¥
    -0.09
    Ñģал
    -0.09
     controlled
    -0.09
    åĩłå®¶
    -0.08
    大å®Ĺ
    -0.08
    POSITIVE LOGITS
    åıĮæĸ¹
    0.13
    çł´è£Ĥ
    0.13
    é»ĺå¥ij
    0.11
     Mutual
    0.11
    ä¿®å¤į
    0.11
    纽带
    0.10
    两个人
    0.10
    mut
    0.10
    缸çĪ±
    0.10
    åĴĮçĿ¦
    0.10
    Activations Density 0.103%

    No Known Activations