© 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. 22271
    Prev
    Next
    INDEX
    Explanations

    algorithms

    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
    ŀ
    -0.09
    ãģ£ãģįãĤĬ
    -0.09
    fo
    -0.08
    nda
    -0.08
     dÃłng
    -0.08
    鸳
    -0.08
    efined
    -0.08
    åĽŀé¦ĸ
    -0.08
     rÃłng
    -0.08
    еÑĩ
    -0.08
    POSITIVE LOGITS
    ically
    0.13
    ic
    0.13
    ions
    0.10
    à¹Į
    0.10
    ally
    0.09
    matic
    0.09
    sg
    0.09
    奶ç²ī
    0.09
    è¿Ļä¸Ģ天
    0.08
    æ²Į
    0.08
    Activations Density 0.022%

    No Known Activations