© 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. 11491
    Prev
    Next
    INDEX
    Explanations

    identity and identification

    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
    å¿Į
    -0.10
     depression
    -0.09
    åĽļ
    -0.09
    æľīä¸Ģ次
    -0.09
    ä¸Ģéģĵ
    -0.09
    æĬijéĥģ
    -0.09
    æĭį
    -0.09
    éģij
    -0.09
    åı¯è§Ĥ
    -0.09
    éŃĤ
    -0.09
    POSITIVE LOGITS
    身份
    0.16
     identity
    0.14
    æĺ¯è°ģ
    0.14
    identity
    0.13
     Identity
    0.12
     anonymity
    0.11
    åĮ¿åIJį
    0.11
     identities
    0.11
    _identity
    0.11
    çļĦ身份
    0.11
    Activations Density 0.095%

    No Known Activations