© 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. 19575
    Prev
    Next
    INDEX
    Explanations

    FILE documents

    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
    AMPL
    -0.11
     Craw
    -0.11
    çĶ»
    -0.09
    æ³µ
    -0.09
    .cz
    -0.09
    bounce
    -0.09
    æ°Ķ象
    -0.09
     craw
    -0.09
    èĨı
    -0.09
    çѵ
    -0.09
    POSITIVE LOGITS
    夹
    0.12
    ä»
    0.12
    å¤įåį°ä»¶
    0.12
     document
    0.11
    çĽĸ
    0.11
     documents
    0.11
    å¤įåį°
    0.10
    æ¡£æ¡Ī
    0.10
    documents
    0.10
    èĵĭ
    0.09
    Activations Density 0.084%

    No Known Activations