© 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. 62589
    Prev
    Next
    INDEX
    Explanations

    primary and secondary

    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
    éĤ£éĩĮ
    -0.09
    åľ¨åIJĮä¸Ģ
    -0.09
    AME
    -0.08
    iter
    -0.08
    ä¼ļè®©ä½ł
    -0.08
    èĢĮåİ»
    -0.08
    ably
    -0.08
    çĤķ
    -0.08
    å¢ĵ
    -0.08
    igrams
    -0.08
    POSITIVE LOGITS
    -secondary
    0.14
    secondary
    0.14
    _secondary
    0.13
     Secondary
    0.12
     secondary
    0.12
    Secondary
    0.12
    .secondary
    0.11
    (primary
    0.10
    /basic
    0.10
    çľĩ
    0.09
    Activations Density 0.114%

    No Known Activations