© 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. 58217
    Prev
    Next
    INDEX
    Explanations

    operating system

    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
    ocity
    -0.09
    è§ĤéŁ³
    -0.09
    æĺİæĺ¾çļĦ
    -0.09
    æĮijåīĶ
    -0.09
    å¿ĥæĢĿ
    -0.09
    çŁį
    -0.09
    åIJ¸
    -0.08
    ç»Ĩå¾®
    -0.08
    /she
    -0.08
    uced
    -0.08
    POSITIVE LOGITS
    ically
    0.09
    ERO
    0.08
    ieri
    0.08
    åıĬ缸åħ³
    0.08
    rag
    0.08
     zach
    0.08
    MLE
    0.08
    çĤ¹åĩ»æŁ¥çľĭ
    0.08
    课
    0.08
    VENT
    0.08
    Activations Density 0.034%

    No Known Activations