© 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. 26817
    Prev
    Next
    INDEX
    Explanations

    conscience, conscientiousness, sane, remorse

    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
    inate
    -0.10
    ied
    -0.09
    .setFocus
    -0.08
    足迹
    -0.08
     Sao
    -0.08
    itarian
    -0.08
    ura
    -0.08
    ost
    -0.08
    ugen
    -0.08
    bers
    -0.08
    POSITIVE LOGITS
    lessly
    0.13
    èī¯å¿ĥ
    0.11
    ê»ı
    0.11
    ably
    0.11
     conscience
    0.10
    ä¸Ģ个éĹ®é¢ĺ
    0.10
    豸
    0.10
    èĤł
    0.09
    adel
    0.09
    ãģ¾ãģ¾
    0.09
    Activations Density 0.003%

    No Known Activations