© 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. 21632
    Prev
    Next
    INDEX
    Explanations

    department of corrections

    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
    çĭIJ
    -0.10
    é»ĺå¥ij
    -0.10
    åī¯
    -0.09
    æīģ
    -0.09
    æĪijè®°å¾Ĺ
    -0.09
    lime
    -0.09
    éĿ³
    -0.09
    ç§ĺ书
    -0.08
    åħĦ
    -0.08
    åħ¬å¼Ģåıij
    -0.08
    POSITIVE LOGITS
    çĽijçĭ±
    0.12
    康å¤į
    0.10
    磫
    0.10
     offender
    0.10
     sentencing
    0.10
     rehab
    0.10
     rehabilit
    0.09
     rehabilitation
    0.09
    çĭ±
    0.09
    ìĭľìĦ¤
    0.09
    Activations Density 0.266%

    No Known Activations