© 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. 56468
    Prev
    Next
    INDEX
    Explanations

    retrospective review or analysis

    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
    å½¢æĢģ
    -0.10
     Ãľ
    -0.09
    夥
    -0.09
    éĩįå¤į
    -0.08
    WEEN
    -0.08
     Flem
    -0.08
    踽
    -0.08
    ä¿Ŀ
    -0.08
     Ebay
    -0.08
    æī¿åĬŀ
    -0.08
    POSITIVE LOGITS
     retro
    0.20
    溯
    0.19
     retrospective
    0.18
     Retro
    0.17
     retrospect
    0.16
     hindsight
    0.16
    追溯
    0.15
    indsight
    0.14
    å¾Ģäºĭ
    0.14
     retrofit
    0.14
    Activations Density 0.164%

    No Known Activations