© 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. 58984
    Prev
    Next
    INDEX
    Explanations

    lonely, loneliness, alone

    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
    ÑĩаÑĤ
    -0.11
    аÑĤелÑĮ
    -0.10
    noon
    -0.09
    ursive
    -0.09
    ëģĶ
    -0.08
    çªľ
    -0.08
    ÑĢад
    -0.08
    atten
    -0.08
    ipple
    -0.08
     Crimson
    -0.08
    POSITIVE LOGITS
     Ñģобой
    0.10
    ties
    0.10
    nier
    0.10
    è¯Ŀ说
    0.09
    sters
    0.09
    ancy
    0.09
    çĹĩ
    0.09
    lier
    0.09
    ä¼ģä¸ļåľ¨
    0.08
    å¯Ĥå¯ŀ
    0.08
    Activations Density 0.004%

    No Known Activations