© 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. 19335
    Prev
    Next
    INDEX
    Explanations

    choose from

    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
    çĥ
    -0.09
    èĬĿ麻
    -0.08
    çľĭè¿ĩ
    -0.08
    å¤ĸç±į
    -0.08
    æķķ
    -0.08
    ä»ĸä¼ļ
    -0.08
    ç«Ń
    -0.08
    ãģ²
    -0.08
    åij½ä¸Ń
    -0.08
    .promise
    -0.08
    POSITIVE LOGITS
    clo
    0.10
     Cres
    0.10
    RTL
    0.09
    anos
    0.09
    OrNull
    0.09
    ç»´å°Ķ
    0.09
    rtl
    0.09
    å²ŃåįĹ
    0.09
     desn
    0.08
     corners
    0.08
    Activations Density 0.090%

    No Known Activations