© 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. 4506
    Prev
    Next
    INDEX
    Explanations

    company names and personal names

    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
    1
    -0.09
     retr
    -0.09
    oster
    -0.09
    5
    -0.08
     packed
    -0.08
    -0.08
    2
    -0.08
    atar
    -0.08
    9
    -0.07
    è¡Įäºĭ
    -0.07
    POSITIVE LOGITS
    .GetProperty
    0.11
    /rfc
    0.10
    .hasMore
    0.10
    AndView
    0.10
    ä¹Łä¸įæķ¢
    0.10
    é¢Ħè§ģ
    0.10
    åįıåĬŀ
    0.10
    HeaderCode
    0.10
    /oauth
    0.09
    缯
    0.09
    Activations Density 0.077%

    No Known Activations