© 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. 63349
    Prev
    Next
    INDEX
    Explanations

    Freud repressed subconscious memory

    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
    à¸ĩ
    -0.10
    ä¸Ĭä¸ĭ
    -0.09
    æĤħ
    -0.09
    å¼ĩ
    -0.09
    çĤ¹å¤´
    -0.09
    æĥľ
    -0.09
    æĺ¯ä¸Ģ项
    -0.08
    æĤ¦
    -0.08
    .docs
    -0.08
    å¼Ģåı£
    -0.08
    POSITIVE LOGITS
     subconscious
    0.12
    æ½ľ
    0.11
     Freud
    0.11
    çĦ¦èĻij
    0.10
     memory
    0.10
    çĸĶ
    0.09
    æ½Ľ
    0.09
     Sho
    0.09
    memory
    0.09
    åĨħåŃĺ
    0.09
    Activations Density 0.069%

    No Known Activations