© 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. 48888
    Prev
    Next
    INDEX
    Explanations

    religious institutions and place names

    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
    æ»ļæ»ļ
    -0.10
    èIJ¥åķĨ
    -0.10
    åħ±çĶŁ
    -0.09
     Banc
    -0.09
     Draft
    -0.09
    è¶ħé«ĺ
    -0.09
    éŀĺ
    -0.09
    Draft
    -0.09
     rap
    -0.09
    æ¯ĶæĪij
    -0.08
    POSITIVE LOGITS
    ilon
    0.10
    LETE
    0.09
    åħĪè¡Į
    0.08
     russe
    0.08
    _REGISTRY
    0.08
    鸦
    0.08
    å±ķå¼Ģ
    0.08
    /rs
    0.08
     Hawkins
    0.08
    追
    0.08
    Activations Density 0.109%

    No Known Activations