© 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. 58102
    Prev
    Next
    INDEX
    Explanations

    Christ

    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
    ç£ķ
    -0.10
    éĴ§
    -0.09
    obb
    -0.09
    宪æ³ķ
    -0.09
    天ä¸ĭ
    -0.09
     wise
    -0.09
     GN
    -0.08
    åĶ¬
    -0.08
    oba
    -0.08
    OperationException
    -0.08
    POSITIVE LOGITS
    ward
    0.09
    åıĬåħ¶
    0.09
    ians
    0.08
    ium
    0.08
    ancer
    0.08
    梼
    0.08
    æ°¸ä¸į
    0.08
    æĻļæľŁ
    0.08
    çķĻè¨ĢæĿ¿
    0.08
    æµ®
    0.08
    Activations Density 0.009%

    No Known Activations