© 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. 7240
    Prev
    Next
    INDEX
    Explanations

    maintenance and upkeep

    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
    sWith
    -0.12
    erator
    -0.10
    ../../../
    -0.10
    ter
    -0.10
    erate
    -0.10
    çĭ¸
    -0.10
    å½»
    -0.10
    åŃIJéĩĮ
    -0.10
    ãģĦãĤĭ
    -0.09
    ä»Ģä¹Īæł·
    -0.09
    POSITIVE LOGITS
    lew
    0.10
    visor
    0.09
     SEAL
    0.09
    agr
    0.09
    SEA
    0.08
    翼
    0.08
    eq
    0.08
    eam
    0.08
     Seal
    0.08
    imap
    0.08
    Activations Density 0.008%

    No Known Activations