© 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. 30693
    Prev
    Next
    INDEX
    Explanations

    suffixes and acronyms

    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
    IOR
    -0.09
    èĬ¬
    -0.09
    è±ķ
    -0.09
    çĻ¾èĬ±
    -0.09
    åłµ
    -0.09
    _SEG
    -0.09
    æºĥ
    -0.08
    pig
    -0.08
    atar
    -0.08
    éªł
    -0.08
    POSITIVE LOGITS
    AndGet
    0.09
    æĵį纵
    0.09
    esch
    0.08
    å®īåħ¨ä¿Ŀéļľ
    0.08
    èĪ¹åıª
    0.08
    æŀģ端
    0.08
    çİ»
    0.08
    ecs
    0.08
    abo
    0.08
    å¯Ł
    0.08
    Activations Density 0.066%

    No Known Activations