© 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. 50484
    Prev
    Next
    INDEX
    Explanations

    login and credentials

    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
    åĪĽéĢłåĩº
    -0.09
    éĤº
    -0.09
    稷
    -0.09
    ä¾Ħ
    -0.09
    éĹ»
    -0.09
    .generated
    -0.09
    åı¯çĪ±
    -0.09
    åIJĮä»ģ
    -0.09
    åı«
    -0.08
    主èIJ¥
    -0.08
    POSITIVE LOGITS
    beros
    0.10
     bears
    0.09
    /MIT
    0.08
    ä¸Ģç«Ļ
    0.08
     Forget
    0.08
    ior
    0.08
    åĩŃ
    0.08
    èľľ
    0.08
    identity
    0.08
    æŁĶåĴĮ
    0.08
    Activations Density 0.232%

    No Known Activations