© 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. 34899
    Prev
    Next
    INDEX
    Explanations

    mediation & trade agreements

    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
    èĶ¼
    -0.11
     DÅ©ng
    -0.09
    轶
    -0.09
    /or
    -0.08
    rew
    -0.08
    åĸĦæĦı
    -0.08
    enk
    -0.08
    ë¥ĺ
    -0.08
    ฯ
    -0.08
    Cos
    -0.08
    POSITIVE LOGITS
    éta
    0.09
    senal
    0.08
    licher
    0.08
    emie
    0.08
    >Your
    0.08
    .pkg
    0.08
    vester
    0.07
    trial
    0.07
    replacement
    0.07
    aren
    0.07
    Activations Density 0.471%

    No Known Activations