© 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. 33853
    Prev
    Next
    INDEX
    Explanations

    pronouns: you, me, my, I

    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
    èĮµ
    -0.09
    çĦī
    -0.09
    æ¼ķ
    -0.08
    åĿ·
    -0.08
    Elem
    -0.08
    rev
    -0.08
    æĬ½åıĸ
    -0.08
    çīĿ
    -0.07
    å·§å¦Ļ
    -0.07
     Bes
    -0.07
    POSITIVE LOGITS
     vos
    0.10
    媽
    0.10
    åĴĮä»ĸçļĦ
    0.10
    _stderr
    0.10
    innen
    0.10
    éĢĢå½¹
    0.09
    åħ³ç³»
    0.09
    ìłĢ
    0.09
    éĻ
    0.09
     Bent
    0.09
    Activations Density 0.188%

    No Known Activations