© 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. 11806
    Prev
    Next
    INDEX
    Explanations

    study of

    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
    ç§ijçłĶ
    -0.10
    鸢
    -0.10
    ạ
    -0.10
    æ¡ĤæŀĹ
    -0.10
    çķĭ
    -0.10
     savedInstanceState
    -0.09
    åĨķ
    -0.09
    alin
    -0.09
     tertiary
    -0.09
    çıłæµ·
    -0.09
    POSITIVE LOGITS
    æ¸ħæ¥ļ
    0.09
    å¦Ĥä½ķ
    0.09
    å¦Ĥä½ķåİ»
    0.09
    é¹ij
    0.08
     how
    0.08
     topics
    0.08
    åĻĻ
    0.08
    è¿Ļæĸ¹éĿ¢
    0.08
    å°§
    0.08
    åĵĨ
    0.08
    Activations Density 0.255%

    No Known Activations