© 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. 38986
    Prev
    Next
    INDEX
    Explanations

    doom, alarm, falling, naysayers

    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
    åħ¨æĹ¥
    -0.10
    Occurred
    -0.10
    ç¥ŀåľ£
    -0.10
    äºĶå®ĺ
    -0.09
     strained
    -0.09
    è°ļ
    -0.09
    åħ¨å®¶
    -0.09
    mons
    -0.09
    .normalized
    -0.09
    èIJ¥
    -0.09
    POSITIVE LOGITS
    æĤ²è§Ĥ
    0.18
     pessim
    0.14
    ä¹IJè§Ĥ
    0.11
     depressing
    0.11
     bleak
    0.11
     doom
    0.11
    æĿŀ
    0.10
    笼罩
    0.10
     glo
    0.09
    çģı
    0.09
    Activations Density 0.033%

    No Known Activations