© 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. 55916
    Prev
    Next
    INDEX
    Explanations

    righteousness, deed, altruism

    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
    ä¸Ģçľ¼
    -0.09
    çľĭ好
    -0.09
    æĹ¥æĬ¥ç¤¾
    -0.09
    iti
    -0.09
    è¿ĺæľīä»Ģä¹Ī
    -0.08
    çĨ
    -0.08
    纵
    -0.08
    享åıĹ
    -0.08
    åłĨ
    -0.08
    解éĻ¤
    -0.08
    POSITIVE LOGITS
    é«ĺå°ļ
    0.10
    enso
    0.09
    .iso
    0.09
    åı¯æĥľ
    0.09
    endant
    0.09
    èĩªè§ī
    0.09
    åħ¸èĮĥ
    0.09
    ä¹ĭå¿ĥ
    0.09
    满满
    0.09
    -hearted
    0.09
    Activations Density 0.150%

    No Known Activations