© 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. 32705
    Prev
    Next
    INDEX
    Explanations

    traumatic conditions

    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
    owing
    -0.11
    esto
    -0.11
    hood
    -0.10
    ings
    -0.10
     dÃłng
    -0.10
    çĭIJ
    -0.10
    obe
    -0.09
    Ñģ
    -0.09
    ration
    -0.09
    band
    -0.09
    POSITIVE LOGITS
    ĵ
    0.09
    ä¹ĭä½Ļ
    0.09
    jectories
    0.09
    asc
    0.09
    ãģĹãĤĩãģĨ
    0.08
    áºłI
    0.08
    alse
    0.08
    ÙĬست
    0.08
     Emmy
    0.08
    æĢ§çļĦ
    0.08
    Activations Density 0.014%

    No Known Activations