© 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. 54716
    Prev
    Next
    INDEX
    Explanations

    cryptographic libraries

    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
    artz
    -0.09
    å±Ĥåĩº
    -0.08
    ATS
    -0.08
    å·©
    -0.08
    åłĨ
    -0.08
    ignal
    -0.08
     Lans
    -0.08
    产éĶĢ
    -0.08
     BuzzFeed
    -0.08
    porto
    -0.08
    POSITIVE LOGITS
    éŃģ
    0.08
    çĸ®
    0.08
    eenth
    0.08
    åIJĮèĥŀ
    0.08
    åĮĸè¿Ľç¨ĭ
    0.08
    ведиÑĤе
    0.08
    çľ©
    0.08
    禾
    0.08
    æ¿Ģæĥħ
    0.08
    بس
    0.08
    Activations Density 0.002%

    No Known Activations