© 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. 63144
    Prev
    Next
    INDEX
    Explanations

    discussing truth claims

    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
    麻
    -0.10
    oki
    -0.09
     wings
    -0.09
    .Priority
    -0.09
    _RETRY
    -0.09
    æĪIJåĬŁçİĩ
    -0.09
    ronic
    -0.09
    _VALIDATE
    -0.08
    çīĪæĿĥ声æĺİ
    -0.08
    Principal
    -0.08
    POSITIVE LOGITS
    çļĦ第ä¸Ģ
    0.09
    ä¸įæŃ¢
    0.09
    OID
    0.09
    åŀĦæĸŃ
    0.08
    dera
    0.08
    æĬł
    0.08
    ubyte
    0.08
    amar
    0.08
    losure
    0.08
    å°º
    0.08
    Activations Density 0.201%

    No Known Activations