© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21622
    Prev
    Next
    INDEX
    Explanations

    struct TreeNode

    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
    没åĬŀæ³ķ
    -0.08
    ç¾İåĽ¢
    -0.08
    çİł
    -0.08
    ذر
    -0.08
    åħ¬äº¤
    -0.08
     sigh
    -0.08
    åħļæĶ¿
    -0.08
    izzard
    -0.08
    /*@
    -0.07
     TreeMap
    -0.07
    POSITIVE LOGITS
    èĵ¼
    0.09
    å¡ŀ
    0.08
    çĽ¸ä¼ł
    0.08
    abra
    0.08
    ibase
    0.08
    بار
    0.08
    _PORTS
    0.08
     ragaz
    0.08
    alis
    0.08
    å¹²çĩ¥
    0.08
    Activations Density 0.416%

    No Known Activations