© 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. 47967
    Prev
    Next
    INDEX
    Explanations

    friends and adding friends

    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
    Donald
    -0.09
    çĦ¦
    -0.09
     Donald
    -0.08
    åĩºçĶŁ
    -0.08
    QUAL
    -0.08
     Redistributions
    -0.08
     dictatorship
    -0.08
    راÙĨ
    -0.08
    å±Ģéĥ¨
    -0.08
     Coalition
    -0.08
    POSITIVE LOGITS
    好åıĭ
    0.13
    伸æīĭ
    0.11
    æŃ¤äºº
    0.10
    人èĦī
    0.10
    éĿ¢å¯¹éĿ¢
    0.10
    ASHBOARD
    0.09
    çĶ©
    0.09
    çļĦåħ³æ³¨
    0.09
    åĦ¿ç§ij
    0.09
    ircle
    0.09
    Activations Density 0.077%

    No Known Activations