© 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. 49149
    Prev
    Next
    INDEX
    Explanations

    that the

    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
    åĵī
    -0.10
    alla
    -0.09
    ден
    -0.09
    _COMPILE
    -0.08
    /native
    -0.08
    yll
    -0.08
    æĪijçĽ¸ä¿¡
    -0.08
    ä¿¡ä»»
    -0.08
    iland
    -0.08
    ç¬ijäºĨ
    -0.08
    POSITIVE LOGITS
    aida
    0.11
    å·²ä¹ħçļĦ
    0.10
    è¿Ļè¾ĪåŃIJ
    0.10
    该项
    0.10
    heel
    0.09
    çĵ£
    0.09
    头
    0.09
    æīĪ
    0.09
    åİ»åģļ
    0.09
    çŁŃæľŁåĨħ
    0.09
    Activations Density 0.058%

    No Known Activations