© 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. 16954
    Prev
    Next
    INDEX
    Explanations

    psychoanalysis, Freud, ego

    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
    è¯ł
    -0.09
    çīĪæĿĥå½ĴåİŁ
    -0.09
    åı·
    -0.08
    à¹ģà¸Ĥà¸Ļ
    -0.08
    ç»ı纬
    -0.08
    .design
    -0.08
    sembler
    -0.08
    ç¥ŀå·ŀ
    -0.08
    è¸Ŀ
    -0.08
    å¤į
    -0.08
    POSITIVE LOGITS
    æĬķ注
    0.11
    åĪĨæŀIJå¸Ī
    0.09
     Freud
    0.09
    ä¿İ
    0.09
    aju
    0.09
    æĿ¥è®¿
    0.09
    é¼¹
    0.08
     ego
    0.08
     gou
    0.08
    渣
    0.08
    Activations Density 0.101%

    No Known Activations