© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9460
    Prev
    Next
    INDEX
    Explanations

    captain (followed by of team/role or name)

    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
    noc
    -0.09
    amp
    -0.09
    hound
    -0.09
     kup
    -0.09
    aptive
    -0.08
    entifier
    -0.08
    eming
    -0.08
    erner
    -0.08
     khỼp
    -0.08
    erate
    -0.08
    POSITIVE LOGITS
    cies
    0.13
    cy
    0.13
    ialis
    0.10
    å¨ĺ
    0.10
     ÙĪاÙĦÙģ
    0.09
    åĵ¡
    0.09
    æºī
    0.09
    å¦Ĥæŀľè¯´
    0.09
    ¿
    0.09
    леÑĤ
    0.09
    Activations Density 0.014%

    No Known Activations