© 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. 18873
    Prev
    Next
    INDEX
    Explanations

    ethical, moral, psychological, emotional, aesthetic considerations

    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
    дон
    -0.09
    getResponse
    -0.08
    عار
    -0.08
    ä¸į失
    -0.08
     ferr
    -0.08
    æĦŁæĤŁ
    -0.08
    èĨº
    -0.08
    Declared
    -0.08
    door
    -0.07
     Dale
    -0.07
    POSITIVE LOGITS
    åĽłç´ł
    0.13
    åĴĮæĬĢæľ¯
    0.11
    åİŁåĽł
    0.10
     reasons
    0.10
    æį
    0.10
     considerations
    0.09
    åĽŀäºĭ
    0.09
    èĢĮè¨Ģ
    0.09
    æĢµ
    0.09
    ishly
    0.09
    Activations Density 0.099%

    No Known Activations