© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51610
    Prev
    Next
    INDEX
    Explanations

    deception detection

    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
    uated
    -0.10
    maal
    -0.09
    å§Ķ书记
    -0.09
    abouts
    -0.09
    eros
    -0.08
    åijµæĬ¤
    -0.08
    æķijåij½
    -0.08
    itud
    -0.08
    å²±
    -0.08
    ainer
    -0.08
    POSITIVE LOGITS
    ively
    0.16
    æĦł
    0.10
    ives
    0.10
    á¹Ń
    0.09
    çi
    0.09
    åĺŀ
    0.09
    çĺ¸
    0.09
    æĻ°
    0.09
    ambre
    0.09
    /ion
    0.08
    Activations Density 0.005%

    No Known Activations