© 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. 28094
    Prev
    Next
    INDEX
    Explanations

    functioning properly

    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
    åĿĬ
    -0.09
    vore
    -0.09
    éľ²
    -0.09
    åħħå®ŀ
    -0.08
    logan
    -0.08
    çĶŁé²ľ
    -0.08
    agner
    -0.08
    .Orientation
    -0.08
    è¯Ĭ
    -0.08
    illé
    -0.08
    POSITIVE LOGITS
    æŃ£å¸¸çļĦ
    0.16
    æŃ£å¸¸
    0.15
     долж
    0.13
     normal
    0.13
    éĶ¡
    0.11
    proper
    0.11
     proper
    0.11
    æŃ£å¸¸ä½¿çĶ¨
    0.11
     ability
    0.11
    åºĶæľīçļĦ
    0.11
    Activations Density 0.460%

    No Known Activations