© 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. 29994
    Prev
    Next
    INDEX
    Explanations

    morals and morality

    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
    artment
    -0.09
    欺
    -0.09
    ÑĪÑĥ
    -0.08
    æĶ¿æĿĥ
    -0.08
    oma
    -0.08
    áĥ«
    -0.08
    -sizing
    -0.08
    æĢª
    -0.08
    åıijçĶµæľº
    -0.08
    åij»
    -0.08
    POSITIVE LOGITS
    éģĵå¾·
    0.13
    伦çIJĨ
    0.10
     morals
    0.10
    èī¯å¿ĥ
    0.10
     moral
    0.10
    å·¥ç¨ĭ建设
    0.10
    çķĮçļĦ
    0.10
    ä¿®åħ»
    0.10
    istic
    0.09
    å»ī
    0.09
    Activations Density 0.020%

    No Known Activations