© 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. 35853
    Prev
    Next
    INDEX
    Explanations

    to make money

    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£ä¹Ī容æĺĵ
    -0.10
    æİı
    -0.09
    èĬĤ约
    -0.09
    åıĭæĥħ
    -0.08
    imson
    -0.08
    éĿł
    -0.08
    åĩŃ
    -0.08
    oven
    -0.08
    å¶Ĥ
    -0.08
     Blasio
    -0.08
    POSITIVE LOGITS
     PRIV
    0.09
    循
    0.08
    æĮº
    0.08
    ç³Ł
    0.08
    omial
    0.08
    åĭī强
    0.08
    .priv
    0.08
    ãģ£ãģį
    0.08
    pile
    0.08
    деÑģÑı
    0.08
    Activations Density 0.032%

    No Known Activations