© 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. 53732
    Prev
    Next
    INDEX
    Explanations

    trust and reliability

    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
    æ·«
    -0.10
    cors
    -0.09
     æĸ
    -0.09
    (Size
    -0.09
    .ordinal
    -0.09
    rimp
    -0.08
    ç¼Ģ
    -0.08
     entertaining
    -0.08
     orth
    -0.08
    åĭ¿
    -0.08
    POSITIVE LOGITS
    ä¿¡ä»»
    0.38
    çļĦä¿¡ä»»
    0.33
     trust
    0.28
    ä¿¡èµĸ
    0.28
     Trust
    0.24
    Trust
    0.23
    trust
    0.22
    ä¿¡æīĺ
    0.20
     trusting
    0.20
     trusts
    0.20
    Activations Density 0.056%

    No Known Activations