© 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. 52389
    Prev
    Next
    INDEX
    Explanations

    chance, saving, bonus, project

    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
    é«»
    -0.10
    åĪĽæĦı
    -0.09
    çĥĿ
    -0.09
    å¸Ĥåľºç»ıæµİ
    -0.09
    管çIJĨåĬŀæ³ķ
    -0.09
    åķĨæľº
    -0.08
    lington
    -0.08
    .Sum
    -0.08
    é¦Ħ
    -0.08
    åħħ满äºĨ
    -0.08
    POSITIVE LOGITS
    ToEnd
    0.09
    xe
    0.09
    赶ä¸Ĭ
    0.09
     chance
    0.08
    illi
    0.08
    astes
    0.08
    çŃī级
    0.08
    imap
    0.08
    觥
    0.08
    zes
    0.08
    Activations Density 0.045%

    No Known Activations