© 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. 38903
    Prev
    Next
    INDEX
    Explanations

    charged, scheduled, released, fined

    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
    è¿Ļä¹Ī说
    -0.09
    çĶŁæĢķ
    -0.09
    phans
    -0.09
     CURL
    -0.08
    åħ³çĪ±
    -0.08
     requis
    -0.08
    人éĢī
    -0.08
    ØŃس
    -0.08
    çľģæĶ¿åºľ
    -0.08
     Gone
    -0.08
    POSITIVE LOGITS
     Sof
    0.09
    ç¾ģ
    0.09
    女åŃIJ
    0.09
    å¤ĩ
    0.08
    aney
    0.08
    被åĪ¤
    0.08
    .decorate
    0.08
    åĢį
    0.08
    éĺħ读åħ¨æĸĩ
    0.08
    aded
    0.08
    Activations Density 0.027%

    No Known Activations